< Prev | Home | Model | Random | Next >

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

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

Neuron 1346 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 2.6892. Min Range: -2.6892

Max Act: 2.6892. Min Act: -0.1700

Data Index: 99386 (C4 (Web Text))

Max Activating Token Index: 593

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 2.6892. Min Range: -2.6892

Max Act: 2.6572. Min Act: -0.1700

Data Index: 388977 (C4 (Web Text))

Max Activating Token Index: 500

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 2.6892. Min Range: -2.6892

Max Act: 2.5607. Min Act: -0.1700

Data Index: 791296 (C4 (Web Text))

Max Activating Token Index: 696

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 2.6892. Min Range: -2.6892

Max Act: 2.5445. Min Act: -0.1700

Data Index: 366219 (C4 (Web Text))

Max Activating Token Index: 82

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 2.6892. Min Range: -2.6892

Max Act: 2.5445. Min Act: -0.1700

Data Index: 914359 (C4 (Web Text))

Max Activating Token Index: 711

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 2.6892. Min Range: -2.6892

Max Act: 2.5284. Min Act: -0.1700

Data Index: 1015917 (C4 (Web Text))

Max Activating Token Index: 221

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 2.6892. Min Range: -2.6892

Max Act: 2.5284. Min Act: -0.1700

Data Index: 206603 (C4 (Web Text))

Max Activating Token Index: 777

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 2.6892. Min Range: -2.6892

Max Act: 2.5122. Min Act: -0.1700

Data Index: 540217 (C4 (Web Text))

Max Activating Token Index: 77

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 2.6892. Min Range: -2.6892

Max Act: 2.5284. Min Act: -0.1700

Data Index: 725232 (C4 (Web Text))

Max Activating Token Index: 512

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 2.6892. Min Range: -2.6892

Max Act: 2.5122. Min Act: -0.1700

Data Index: 447458 (C4 (Web Text))

Max Activating Token Index: 72

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 2.6892. Min Range: -2.6892

Max Act: 2.5122. Min Act: -0.1700

Data Index: 836883 (C4 (Web Text))

Max Activating Token Index: 65

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 2.6892. Min Range: -2.6892

Max Act: 2.4960. Min Act: -0.1700

Data Index: 1417383 (Python Code)

Max Activating Token Index: 353

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 2.6892. Min Range: -2.6892

Max Act: 2.4960. Min Act: -0.1700

Data Index: 818504 (C4 (Web Text))

Max Activating Token Index: 290

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 2.6892. Min Range: -2.6892

Max Act: 2.4798. Min Act: -0.1700

Data Index: 1214464 (C4 (Web Text))

Max Activating Token Index: 435

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 2.6892. Min Range: -2.6892

Max Act: 2.4798. Min Act: -0.1700

Data Index: 316844 (C4 (Web Text))

Max Activating Token Index: 15

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 2.6892. Min Range: -2.6892

Max Act: 2.4636. Min Act: -0.1700

Data Index: 893441 (C4 (Web Text))

Max Activating Token Index: 8

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 2.6892. Min Range: -2.6892

Max Act: 2.4798. Min Act: -0.1700

Data Index: 1651021 (Python Code)

Max Activating Token Index: 125

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 2.6892. Min Range: -2.6892

Max Act: 2.4473. Min Act: -0.1700

Data Index: 908329 (C4 (Web Text))

Max Activating Token Index: 325

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 2.6892. Min Range: -2.6892

Max Act: 2.4636. Min Act: -0.1700

Data Index: 482562 (C4 (Web Text))

Max Activating Token Index: 624

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 2.6892. Min Range: -2.6892

Max Act: 2.4636. Min Act: -0.1700

Data Index: 562662 (C4 (Web Text))

Max Activating Token Index: 85

Click toggle to see full text

Truncated

Full Text #19