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

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

Neuron 1105 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4393. Min Range: -3.4393

Max Act: 3.4393. Min Act: -0.1700

Data Index: 991509 (C4 (Web Text))

Max Activating Token Index: 728

Text #1

Max Range: 3.4393. Min Range: -3.4393

Max Act: 3.3609. Min Act: -0.1700

Data Index: 818471 (C4 (Web Text))

Max Activating Token Index: 580

Text #2

Max Range: 3.4393. Min Range: -3.4393

Max Act: 3.3609. Min Act: -0.1700

Data Index: 960788 (C4 (Web Text))

Max Activating Token Index: 887

Text #3

Max Range: 3.4393. Min Range: -3.4393

Max Act: 3.3295. Min Act: -0.1700

Data Index: 523845 (C4 (Web Text))

Max Activating Token Index: 343

Text #4

Max Range: 3.4393. Min Range: -3.4393

Max Act: 3.3138. Min Act: -0.1700

Data Index: 1352343 (C4 (Web Text))

Max Activating Token Index: 437

Text #5

Max Range: 3.4393. Min Range: -3.4393

Max Act: 3.2981. Min Act: -0.1700

Data Index: 20143 (C4 (Web Text))

Max Activating Token Index: 435

Text #6

Max Range: 3.4393. Min Range: -3.4393

Max Act: 3.3138. Min Act: -0.1700

Data Index: 860650 (C4 (Web Text))

Max Activating Token Index: 393

Text #7

Max Range: 3.4393. Min Range: -3.4393

Max Act: 3.3138. Min Act: -0.1700

Data Index: 914771 (C4 (Web Text))

Max Activating Token Index: 291

Text #8

Max Range: 3.4393. Min Range: -3.4393

Max Act: 3.2824. Min Act: -0.1700

Data Index: 693537 (C4 (Web Text))

Max Activating Token Index: 563

Text #9

Max Range: 3.4393. Min Range: -3.4393

Max Act: 3.2824. Min Act: -0.1700

Data Index: 843184 (C4 (Web Text))

Max Activating Token Index: 652

Text #10

Max Range: 3.4393. Min Range: -3.4393

Max Act: 3.2509. Min Act: -0.1700

Data Index: 46730 (C4 (Web Text))

Max Activating Token Index: 418

Text #11

Max Range: 3.4393. Min Range: -3.4393

Max Act: 3.2824. Min Act: -0.1700

Data Index: 77283 (C4 (Web Text))

Max Activating Token Index: 182

Text #12

Max Range: 3.4393. Min Range: -3.4393

Max Act: 3.2667. Min Act: -0.1700

Data Index: 528187 (C4 (Web Text))

Max Activating Token Index: 8

Text #13

Max Range: 3.4393. Min Range: -3.4393

Max Act: 3.2667. Min Act: -0.1700

Data Index: 509268 (C4 (Web Text))

Max Activating Token Index: 217

Text #14

Max Range: 3.4393. Min Range: -3.4393

Max Act: 3.2509. Min Act: -0.1700

Data Index: 542808 (C4 (Web Text))

Max Activating Token Index: 903

Text #15

Max Range: 3.4393. Min Range: -3.4393

Max Act: 3.2667. Min Act: -0.1700

Data Index: 1005393 (C4 (Web Text))

Max Activating Token Index: 482

Text #16

Max Range: 3.4393. Min Range: -3.4393

Max Act: 3.2667. Min Act: -0.1700

Data Index: 190323 (C4 (Web Text))

Max Activating Token Index: 396

Text #17

Max Range: 3.4393. Min Range: -3.4393

Max Act: 3.2352. Min Act: -0.1700

Data Index: 630433 (C4 (Web Text))

Max Activating Token Index: 81

Text #18

Max Range: 3.4393. Min Range: -3.4393

Max Act: 3.2352. Min Act: -0.1700

Data Index: 1093871 (C4 (Web Text))

Max Activating Token Index: 952

Text #19

Max Range: 3.4393. Min Range: -3.4393

Max Act: 3.2352. Min Act: -0.1700

Data Index: 1176737 (C4 (Web Text))

Max Activating Token Index: 706