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

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

Neuron 1351 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: 3.7945. Min Range: -3.7945

Max Act: 3.7945. Min Act: -0.1700

Data Index: 521943 (C4 (Web Text))

Max Activating Token Index: 896

Text #1

Max Range: 3.7945. Min Range: -3.7945

Max Act: 3.7945. Min Act: -0.1700

Data Index: 1038051 (C4 (Web Text))

Max Activating Token Index: 155

Text #2

Max Range: 3.7945. Min Range: -3.7945

Max Act: 3.7945. Min Act: -0.1700

Data Index: 574541 (C4 (Web Text))

Max Activating Token Index: 911

Text #3

Max Range: 3.7945. Min Range: -3.7945

Max Act: 3.7945. Min Act: -0.1700

Data Index: 302791 (C4 (Web Text))

Max Activating Token Index: 811

Text #4

Max Range: 3.7945. Min Range: -3.7945

Max Act: 3.7006. Min Act: -0.1700

Data Index: 987524 (C4 (Web Text))

Max Activating Token Index: 158

Text #5

Max Range: 3.7945. Min Range: -3.7945

Max Act: 3.7319. Min Act: -0.1700

Data Index: 228058 (C4 (Web Text))

Max Activating Token Index: 590

Text #6

Max Range: 3.7945. Min Range: -3.7945

Max Act: 3.7006. Min Act: -0.1700

Data Index: 923388 (C4 (Web Text))

Max Activating Token Index: 893

Text #7

Max Range: 3.7945. Min Range: -3.7945

Max Act: 3.7006. Min Act: -0.1700

Data Index: 211804 (C4 (Web Text))

Max Activating Token Index: 586

Text #8

Max Range: 3.7945. Min Range: -3.7945

Max Act: 3.7319. Min Act: -0.1700

Data Index: 482225 (C4 (Web Text))

Max Activating Token Index: 698

Text #9

Max Range: 3.7945. Min Range: -3.7945

Max Act: 3.6693. Min Act: -0.1700

Data Index: 629873 (C4 (Web Text))

Max Activating Token Index: 143

Text #10

Max Range: 3.7945. Min Range: -3.7945

Max Act: 3.6380. Min Act: -0.1700

Data Index: 741347 (C4 (Web Text))

Max Activating Token Index: 294

Text #11

Max Range: 3.7945. Min Range: -3.7945

Max Act: 3.6067. Min Act: -0.1700

Data Index: 1203664 (C4 (Web Text))

Max Activating Token Index: 428

Text #12

Max Range: 3.7945. Min Range: -3.7945

Max Act: 3.7006. Min Act: -0.1700

Data Index: 707158 (C4 (Web Text))

Max Activating Token Index: 664

Text #13

Max Range: 3.7945. Min Range: -3.7945

Max Act: 3.6067. Min Act: -0.1700

Data Index: 679956 (C4 (Web Text))

Max Activating Token Index: 329

Text #14

Max Range: 3.7945. Min Range: -3.7945

Max Act: 3.6380. Min Act: -0.1700

Data Index: 632785 (C4 (Web Text))

Max Activating Token Index: 285

Text #15

Max Range: 3.7945. Min Range: -3.7945

Max Act: 3.6380. Min Act: -0.1700

Data Index: 878600 (C4 (Web Text))

Max Activating Token Index: 418

Text #16

Max Range: 3.7945. Min Range: -3.7945

Max Act: 3.6380. Min Act: -0.1700

Data Index: 246299 (C4 (Web Text))

Max Activating Token Index: 971

Text #17

Max Range: 3.7945. Min Range: -3.7945

Max Act: 3.6067. Min Act: -0.1700

Data Index: 1131842 (C4 (Web Text))

Max Activating Token Index: 334

Text #18

Max Range: 3.7945. Min Range: -3.7945

Max Act: 3.6380. Min Act: -0.1700

Data Index: 1097641 (C4 (Web Text))

Max Activating Token Index: 230

Text #19

Max Range: 3.7945. Min Range: -3.7945

Max Act: 3.6380. Min Act: -0.1700

Data Index: 481847 (C4 (Web Text))

Max Activating Token Index: 161