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

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

Neuron 526 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4315. Min Range: -3.4315

Max Act: 3.4315. Min Act: -0.1700

Data Index: 383126 (C4 (Web Text))

Max Activating Token Index: 997

Text #1

Max Range: 3.4315. Min Range: -3.4315

Max Act: 3.4159. Min Act: -0.1700

Data Index: 245750 (C4 (Web Text))

Max Activating Token Index: 142

Text #2

Max Range: 3.4315. Min Range: -3.4315

Max Act: 3.3845. Min Act: -0.1700

Data Index: 216760 (C4 (Web Text))

Max Activating Token Index: 945

Text #3

Max Range: 3.4315. Min Range: -3.4315

Max Act: 3.3688. Min Act: -0.1700

Data Index: 776421 (C4 (Web Text))

Max Activating Token Index: 341

Text #4

Max Range: 3.4315. Min Range: -3.4315

Max Act: 3.3688. Min Act: -0.1700

Data Index: 336066 (C4 (Web Text))

Max Activating Token Index: 39

Text #5

Max Range: 3.4315. Min Range: -3.4315

Max Act: 3.3688. Min Act: -0.1700

Data Index: 1072936 (C4 (Web Text))

Max Activating Token Index: 36

Text #6

Max Range: 3.4315. Min Range: -3.4315

Max Act: 3.3531. Min Act: -0.1700

Data Index: 272999 (C4 (Web Text))

Max Activating Token Index: 389

Text #7

Max Range: 3.4315. Min Range: -3.4315

Max Act: 3.3060. Min Act: -0.1700

Data Index: 885800 (C4 (Web Text))

Max Activating Token Index: 750

Text #8

Max Range: 3.4315. Min Range: -3.4315

Max Act: 3.3531. Min Act: -0.1700

Data Index: 520815 (C4 (Web Text))

Max Activating Token Index: 45

Text #9

Max Range: 3.4315. Min Range: -3.4315

Max Act: 3.2903. Min Act: -0.1700

Data Index: 352407 (C4 (Web Text))

Max Activating Token Index: 782

Text #10

Max Range: 3.4315. Min Range: -3.4315

Max Act: 3.3374. Min Act: -0.1700

Data Index: 426413 (C4 (Web Text))

Max Activating Token Index: 25

Text #11

Max Range: 3.4315. Min Range: -3.4315

Max Act: 3.3217. Min Act: -0.1700

Data Index: 1263191 (C4 (Web Text))

Max Activating Token Index: 147

Text #12

Max Range: 3.4315. Min Range: -3.4315

Max Act: 3.3531. Min Act: -0.1700

Data Index: 652379 (C4 (Web Text))

Max Activating Token Index: 273

Text #13

Max Range: 3.4315. Min Range: -3.4315

Max Act: 3.3060. Min Act: -0.1700

Data Index: 469093 (C4 (Web Text))

Max Activating Token Index: 831

Text #14

Max Range: 3.4315. Min Range: -3.4315

Max Act: 3.2903. Min Act: -0.1700

Data Index: 1089712 (C4 (Web Text))

Max Activating Token Index: 539

Text #15

Max Range: 3.4315. Min Range: -3.4315

Max Act: 3.3060. Min Act: -0.1700

Data Index: 371253 (C4 (Web Text))

Max Activating Token Index: 152

Text #16

Max Range: 3.4315. Min Range: -3.4315

Max Act: 3.3217. Min Act: -0.1700

Data Index: 537590 (C4 (Web Text))

Max Activating Token Index: 848

Text #17

Max Range: 3.4315. Min Range: -3.4315

Max Act: 3.2746. Min Act: -0.1700

Data Index: 875521 (C4 (Web Text))

Max Activating Token Index: 598

Text #18

Max Range: 3.4315. Min Range: -3.4315

Max Act: 3.2903. Min Act: -0.1700

Data Index: 630674 (C4 (Web Text))

Max Activating Token Index: 196

Text #19

Max Range: 3.4315. Min Range: -3.4315

Max Act: 3.2903. Min Act: -0.1700

Data Index: 777622 (C4 (Web Text))

Max Activating Token Index: 678