< Prev | Home | Model | Random | Next >

Model: GELU Model: 3 Layers, 2048 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 113 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')



Text #0

Max Range: 6.9955. Min Range: -6.9955

Max Act: 6.9955. Min Act: -0.1700

Data Index: 547259 (C4 (Web Text))

Max Activating Token Index: 272

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 6.9955. Min Range: -6.9955

Max Act: 6.9955. Min Act: -0.1700

Data Index: 1491338 (Python Code)

Max Activating Token Index: 388

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 6.9955. Min Range: -6.9955

Max Act: 6.8392. Min Act: -0.1700

Data Index: 502691 (C4 (Web Text))

Max Activating Token Index: 255

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 6.9955. Min Range: -6.9955

Max Act: 6.9017. Min Act: -0.1700

Data Index: 1305053 (C4 (Web Text))

Max Activating Token Index: 266

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 6.9955. Min Range: -6.9955

Max Act: 6.8080. Min Act: -0.1700

Data Index: 1080273 (C4 (Web Text))

Max Activating Token Index: 582

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 6.9955. Min Range: -6.9955

Max Act: 6.7455. Min Act: -0.1700

Data Index: 532297 (C4 (Web Text))

Max Activating Token Index: 267

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 6.9955. Min Range: -6.9955

Max Act: 6.6830. Min Act: -0.1700

Data Index: 1569875 (Python Code)

Max Activating Token Index: 667

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 6.9955. Min Range: -6.9955

Max Act: 6.7455. Min Act: -0.1700

Data Index: 833921 (C4 (Web Text))

Max Activating Token Index: 452

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 6.9955. Min Range: -6.9955

Max Act: 6.6205. Min Act: -0.1700

Data Index: 278125 (C4 (Web Text))

Max Activating Token Index: 143

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 6.9955. Min Range: -6.9955

Max Act: 6.6517. Min Act: -0.1700

Data Index: 1168897 (C4 (Web Text))

Max Activating Token Index: 548

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 6.9955. Min Range: -6.9955

Max Act: 6.5892. Min Act: -0.1700

Data Index: 921168 (C4 (Web Text))

Max Activating Token Index: 216

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 6.9955. Min Range: -6.9955

Max Act: 6.5892. Min Act: -0.1700

Data Index: 1079276 (C4 (Web Text))

Max Activating Token Index: 596

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 6.9955. Min Range: -6.9955

Max Act: 6.6205. Min Act: -0.1700

Data Index: 283396 (C4 (Web Text))

Max Activating Token Index: 136

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 6.9955. Min Range: -6.9955

Max Act: 6.5580. Min Act: -0.1700

Data Index: 690548 (C4 (Web Text))

Max Activating Token Index: 830

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 6.9955. Min Range: -6.9955

Max Act: 6.5580. Min Act: -0.1700

Data Index: 651624 (C4 (Web Text))

Max Activating Token Index: 547

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 6.9955. Min Range: -6.9955

Max Act: 6.5267. Min Act: -0.1700

Data Index: 101622 (C4 (Web Text))

Max Activating Token Index: 615

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 6.9955. Min Range: -6.9955

Max Act: 6.5580. Min Act: -0.1700

Data Index: 1152704 (C4 (Web Text))

Max Activating Token Index: 312

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 6.9955. Min Range: -6.9955

Max Act: 6.5580. Min Act: -0.1700

Data Index: 367553 (C4 (Web Text))

Max Activating Token Index: 719

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 6.9955. Min Range: -6.9955

Max Act: 6.5892. Min Act: -0.1700

Data Index: 947412 (C4 (Web Text))

Max Activating Token Index: 150

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 6.9955. Min Range: -6.9955

Max Act: 6.5580. Min Act: -0.1700

Data Index: 1452969 (Python Code)

Max Activating Token Index: 679

Click toggle to see full text

Truncated

Full Text #19