< Prev | Home | Model | Random | Next >

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

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

Neuron 1341 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: 3.1094. Min Range: -3.1094

Max Act: 3.1094. Min Act: -0.1700

Data Index: 189134 (C4 (Web Text))

Max Activating Token Index: 327

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 3.1094. Min Range: -3.1094

Max Act: 3.0621. Min Act: -0.1700

Data Index: 1308596 (C4 (Web Text))

Max Activating Token Index: 596

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 3.1094. Min Range: -3.1094

Max Act: 3.0306. Min Act: -0.1700

Data Index: 859419 (C4 (Web Text))

Max Activating Token Index: 549

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 3.1094. Min Range: -3.1094

Max Act: 2.9673. Min Act: -0.1700

Data Index: 909894 (C4 (Web Text))

Max Activating Token Index: 681

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 3.1094. Min Range: -3.1094

Max Act: 2.9831. Min Act: -0.1700

Data Index: 258176 (C4 (Web Text))

Max Activating Token Index: 287

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 3.1094. Min Range: -3.1094

Max Act: 2.9989. Min Act: -0.1700

Data Index: 343305 (C4 (Web Text))

Max Activating Token Index: 40

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 3.1094. Min Range: -3.1094

Max Act: 2.9831. Min Act: -0.1700

Data Index: 720537 (C4 (Web Text))

Max Activating Token Index: 770

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 3.1094. Min Range: -3.1094

Max Act: 2.9673. Min Act: -0.1700

Data Index: 1648266 (Python Code)

Max Activating Token Index: 403

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 3.1094. Min Range: -3.1094

Max Act: 2.9673. Min Act: -0.1700

Data Index: 1436166 (Python Code)

Max Activating Token Index: 210

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 3.1094. Min Range: -3.1094

Max Act: 2.9673. Min Act: -0.1700

Data Index: 158044 (C4 (Web Text))

Max Activating Token Index: 847

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 3.1094. Min Range: -3.1094

Max Act: 2.9673. Min Act: -0.1700

Data Index: 870275 (C4 (Web Text))

Max Activating Token Index: 638

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 3.1094. Min Range: -3.1094

Max Act: 2.9515. Min Act: -0.1700

Data Index: 1347660 (C4 (Web Text))

Max Activating Token Index: 54

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 3.1094. Min Range: -3.1094

Max Act: 2.9673. Min Act: -0.1700

Data Index: 923759 (C4 (Web Text))

Max Activating Token Index: 17

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 3.1094. Min Range: -3.1094

Max Act: 2.9673. Min Act: -0.1700

Data Index: 98771 (C4 (Web Text))

Max Activating Token Index: 321

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 3.1094. Min Range: -3.1094

Max Act: 2.9515. Min Act: -0.1700

Data Index: 1296470 (C4 (Web Text))

Max Activating Token Index: 830

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 3.1094. Min Range: -3.1094

Max Act: 2.9356. Min Act: -0.1700

Data Index: 169958 (C4 (Web Text))

Max Activating Token Index: 688

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 3.1094. Min Range: -3.1094

Max Act: 2.9673. Min Act: -0.1700

Data Index: 1237538 (C4 (Web Text))

Max Activating Token Index: 866

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 3.1094. Min Range: -3.1094

Max Act: 2.9515. Min Act: -0.1700

Data Index: 486427 (C4 (Web Text))

Max Activating Token Index: 189

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 3.1094. Min Range: -3.1094

Max Act: 2.9515. Min Act: -0.1700

Data Index: 1234051 (C4 (Web Text))

Max Activating Token Index: 624

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 3.1094. Min Range: -3.1094

Max Act: 2.9515. Min Act: -0.1700

Data Index: 944676 (C4 (Web Text))

Max Activating Token Index: 983

Click toggle to see full text

Truncated

Full Text #19