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

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

Neuron 141 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 8.8264. Min Range: -8.8264

Max Act: 8.8264. Min Act: -0.1698

Data Index: 801991 (C4 (Web Text))

Max Activating Token Index: 623

Text #1

Max Range: 8.8264. Min Range: -8.8264

Max Act: 8.7014. Min Act: -0.1700

Data Index: 437006 (C4 (Web Text))

Max Activating Token Index: 579

Text #2

Max Range: 8.8264. Min Range: -8.8264

Max Act: 8.7014. Min Act: -0.1698

Data Index: 1180474 (C4 (Web Text))

Max Activating Token Index: 344

Text #3

Max Range: 8.8264. Min Range: -8.8264

Max Act: 8.4514. Min Act: -0.1689

Data Index: 1276609 (C4 (Web Text))

Max Activating Token Index: 439

Text #4

Max Range: 8.8264. Min Range: -8.8264

Max Act: 8.5139. Min Act: -0.1700

Data Index: 452449 (C4 (Web Text))

Max Activating Token Index: 192

Text #5

Max Range: 8.8264. Min Range: -8.8264

Max Act: 8.4514. Min Act: -0.1700

Data Index: 551616 (C4 (Web Text))

Max Activating Token Index: 277

Text #6

Max Range: 8.8264. Min Range: -8.8264

Max Act: 8.2639. Min Act: -0.1700

Data Index: 817634 (C4 (Web Text))

Max Activating Token Index: 860

Text #7

Max Range: 8.8264. Min Range: -8.8264

Max Act: 8.2014. Min Act: -0.1699

Data Index: 1005173 (C4 (Web Text))

Max Activating Token Index: 116

Text #8

Max Range: 8.8264. Min Range: -8.8264

Max Act: 8.2014. Min Act: -0.1700

Data Index: 427864 (C4 (Web Text))

Max Activating Token Index: 94

Text #9

Max Range: 8.8264. Min Range: -8.8264

Max Act: 8.3264. Min Act: -0.1700

Data Index: 938612 (C4 (Web Text))

Max Activating Token Index: 192

Text #10

Max Range: 8.8264. Min Range: -8.8264

Max Act: 8.2639. Min Act: -0.1700

Data Index: 424552 (C4 (Web Text))

Max Activating Token Index: 285

Text #11

Max Range: 8.8264. Min Range: -8.8264

Max Act: 8.2639. Min Act: -0.1700

Data Index: 836896 (C4 (Web Text))

Max Activating Token Index: 542

Text #12

Max Range: 8.8264. Min Range: -8.8264

Max Act: 8.1389. Min Act: -0.1700

Data Index: 1004911 (C4 (Web Text))

Max Activating Token Index: 136

Text #13

Max Range: 8.8264. Min Range: -8.8264

Max Act: 8.0139. Min Act: -0.1679

Data Index: 1161039 (C4 (Web Text))

Max Activating Token Index: 932

Text #14

Max Range: 8.8264. Min Range: -8.8264

Max Act: 8.2639. Min Act: -0.1699

Data Index: 236081 (C4 (Web Text))

Max Activating Token Index: 835

Text #15

Max Range: 8.8264. Min Range: -8.8264

Max Act: 8.0764. Min Act: -0.1700

Data Index: 102190 (C4 (Web Text))

Max Activating Token Index: 241

Text #16

Max Range: 8.8264. Min Range: -8.8264

Max Act: 8.0764. Min Act: -0.1700

Data Index: 931163 (C4 (Web Text))

Max Activating Token Index: 970

Text #17

Max Range: 8.8264. Min Range: -8.8264

Max Act: 8.1389. Min Act: -0.1700

Data Index: 822308 (C4 (Web Text))

Max Activating Token Index: 767

Text #18

Max Range: 8.8264. Min Range: -8.8264

Max Act: 8.0139. Min Act: -0.1700

Data Index: 380720 (C4 (Web Text))

Max Activating Token Index: 956

Text #19

Max Range: 8.8264. Min Range: -8.8264

Max Act: 8.0139. Min Act: -0.1700

Data Index: 160698 (C4 (Web Text))

Max Activating Token Index: 265