Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 780 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 7.1160. Min Range: -7.1160

Max Act: 7.1160. Min Act: -0.1700

Data Index: 406982 (C4 (Web Text))

Max Activating Token Index: 880

Text #1

Max Range: 7.1160. Min Range: -7.1160

Max Act: 7.0223. Min Act: -0.1698

Data Index: 1293006 (C4 (Web Text))

Max Activating Token Index: 471

Text #2

Max Range: 7.1160. Min Range: -7.1160

Max Act: 6.8348. Min Act: -0.1700

Data Index: 1164362 (C4 (Web Text))

Max Activating Token Index: 788

Text #3

Max Range: 7.1160. Min Range: -7.1160

Max Act: 6.6160. Min Act: -0.1700

Data Index: 340418 (C4 (Web Text))

Max Activating Token Index: 714

Text #4

Max Range: 7.1160. Min Range: -7.1160

Max Act: 6.5535. Min Act: -0.1700

Data Index: 825876 (C4 (Web Text))

Max Activating Token Index: 629

Text #5

Max Range: 7.1160. Min Range: -7.1160

Max Act: 6.5535. Min Act: -0.1700

Data Index: 1322170 (C4 (Web Text))

Max Activating Token Index: 277

Text #6

Max Range: 7.1160. Min Range: -7.1160

Max Act: 6.4598. Min Act: -0.1700

Data Index: 1237453 (C4 (Web Text))

Max Activating Token Index: 467

Text #7

Max Range: 7.1160. Min Range: -7.1160

Max Act: 6.4598. Min Act: -0.1700

Data Index: 416144 (C4 (Web Text))

Max Activating Token Index: 341

Text #8

Max Range: 7.1160. Min Range: -7.1160

Max Act: 6.4910. Min Act: -0.1700

Data Index: 1238832 (C4 (Web Text))

Max Activating Token Index: 235

Text #9

Max Range: 7.1160. Min Range: -7.1160

Max Act: 6.4598. Min Act: -0.1699

Data Index: 431118 (C4 (Web Text))

Max Activating Token Index: 949

Text #10

Max Range: 7.1160. Min Range: -7.1160

Max Act: 6.3348. Min Act: -0.1700

Data Index: 1357492 (C4 (Web Text))

Max Activating Token Index: 792

Text #11

Max Range: 7.1160. Min Range: -7.1160

Max Act: 6.3348. Min Act: -0.1700

Data Index: 1235770 (C4 (Web Text))

Max Activating Token Index: 272

Text #12

Max Range: 7.1160. Min Range: -7.1160

Max Act: 6.3348. Min Act: -0.1700

Data Index: 772301 (C4 (Web Text))

Max Activating Token Index: 873

Text #13

Max Range: 7.1160. Min Range: -7.1160

Max Act: 6.2410. Min Act: -0.1700

Data Index: 181636 (C4 (Web Text))

Max Activating Token Index: 180

Text #14

Max Range: 7.1160. Min Range: -7.1160

Max Act: 6.2723. Min Act: -0.1700

Data Index: 611039 (C4 (Web Text))

Max Activating Token Index: 320

Text #15

Max Range: 7.1160. Min Range: -7.1160

Max Act: 6.2410. Min Act: -0.1700

Data Index: 621374 (C4 (Web Text))

Max Activating Token Index: 536

Text #16

Max Range: 7.1160. Min Range: -7.1160

Max Act: 6.1785. Min Act: -0.1700

Data Index: 682298 (C4 (Web Text))

Max Activating Token Index: 992

Text #17

Max Range: 7.1160. Min Range: -7.1160

Max Act: 6.1473. Min Act: -0.1700

Data Index: 100229 (C4 (Web Text))

Max Activating Token Index: 1005

Text #18

Max Range: 7.1160. Min Range: -7.1160

Max Act: 6.1785. Min Act: -0.1700

Data Index: 234947 (C4 (Web Text))

Max Activating Token Index: 193

Text #19

Max Range: 7.1160. Min Range: -7.1160

Max Act: 6.0848. Min Act: -0.1700

Data Index: 982552 (C4 (Web Text))

Max Activating Token Index: 836