Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1114 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 5.3169. Min Range: -5.3169

Max Act: 5.3169. Min Act: -0.1700

Data Index: 713375 (C4 (Web Text))

Max Activating Token Index: 307

Text #1

Max Range: 5.3169. Min Range: -5.3169

Max Act: 5.2857. Min Act: -0.1700

Data Index: 1013408 (C4 (Web Text))

Max Activating Token Index: 494

Text #2

Max Range: 5.3169. Min Range: -5.3169

Max Act: 5.2544. Min Act: -0.1700

Data Index: 400707 (C4 (Web Text))

Max Activating Token Index: 539

Text #3

Max Range: 5.3169. Min Range: -5.3169

Max Act: 5.2544. Min Act: -0.1700

Data Index: 1204055 (C4 (Web Text))

Max Activating Token Index: 437

Text #4

Max Range: 5.3169. Min Range: -5.3169

Max Act: 5.1919. Min Act: -0.1700

Data Index: 685230 (C4 (Web Text))

Max Activating Token Index: 327

Text #5

Max Range: 5.3169. Min Range: -5.3169

Max Act: 5.1607. Min Act: -0.1700

Data Index: 1213667 (C4 (Web Text))

Max Activating Token Index: 698

Text #6

Max Range: 5.3169. Min Range: -5.3169

Max Act: 5.1919. Min Act: -0.1700

Data Index: 941984 (C4 (Web Text))

Max Activating Token Index: 220

Text #7

Max Range: 5.3169. Min Range: -5.3169

Max Act: 5.1294. Min Act: -0.1700

Data Index: 376305 (C4 (Web Text))

Max Activating Token Index: 416

Text #8

Max Range: 5.3169. Min Range: -5.3169

Max Act: 5.1607. Min Act: -0.1700

Data Index: 37827 (C4 (Web Text))

Max Activating Token Index: 642

Text #9

Max Range: 5.3169. Min Range: -5.3169

Max Act: 5.1919. Min Act: -0.1700

Data Index: 98685 (C4 (Web Text))

Max Activating Token Index: 371

Text #10

Max Range: 5.3169. Min Range: -5.3169

Max Act: 5.1919. Min Act: -0.1700

Data Index: 542798 (C4 (Web Text))

Max Activating Token Index: 628

Text #11

Max Range: 5.3169. Min Range: -5.3169

Max Act: 5.1607. Min Act: -0.1700

Data Index: 1002535 (C4 (Web Text))

Max Activating Token Index: 272

Text #12

Max Range: 5.3169. Min Range: -5.3169

Max Act: 5.1607. Min Act: -0.1700

Data Index: 375322 (C4 (Web Text))

Max Activating Token Index: 252

Text #13

Max Range: 5.3169. Min Range: -5.3169

Max Act: 5.1919. Min Act: -0.1700

Data Index: 923707 (C4 (Web Text))

Max Activating Token Index: 435

Text #14

Max Range: 5.3169. Min Range: -5.3169

Max Act: 5.0982. Min Act: -0.1700

Data Index: 1061230 (C4 (Web Text))

Max Activating Token Index: 896

Text #15

Max Range: 5.3169. Min Range: -5.3169

Max Act: 5.0982. Min Act: -0.1700

Data Index: 89548 (C4 (Web Text))

Max Activating Token Index: 171

Text #16

Max Range: 5.3169. Min Range: -5.3169

Max Act: 5.1294. Min Act: -0.1700

Data Index: 1005508 (C4 (Web Text))

Max Activating Token Index: 505

Text #17

Max Range: 5.3169. Min Range: -5.3169

Max Act: 5.1607. Min Act: -0.1700

Data Index: 699557 (C4 (Web Text))

Max Activating Token Index: 154

Text #18

Max Range: 5.3169. Min Range: -5.3169

Max Act: 5.0982. Min Act: -0.1700

Data Index: 562199 (C4 (Web Text))

Max Activating Token Index: 567

Text #19

Max Range: 5.3169. Min Range: -5.3169

Max Act: 5.1607. Min Act: -0.1700

Data Index: 97127 (C4 (Web Text))

Max Activating Token Index: 601