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

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

Neuron 1693 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: 3.9231. Min Range: -3.9231

Max Act: 3.9231. Min Act: -0.1700

Data Index: 987806 (C4 (Web Text))

Max Activating Token Index: 342

Text #1

Max Range: 3.9231. Min Range: -3.9231

Max Act: 3.8606. Min Act: -0.1700

Data Index: 671137 (C4 (Web Text))

Max Activating Token Index: 110

Text #2

Max Range: 3.9231. Min Range: -3.9231

Max Act: 3.9231. Min Act: -0.1700

Data Index: 1354224 (C4 (Web Text))

Max Activating Token Index: 394

Text #3

Max Range: 3.9231. Min Range: -3.9231

Max Act: 3.8293. Min Act: -0.1700

Data Index: 868754 (C4 (Web Text))

Max Activating Token Index: 548

Text #4

Max Range: 3.9231. Min Range: -3.9231

Max Act: 3.8293. Min Act: -0.1700

Data Index: 324375 (C4 (Web Text))

Max Activating Token Index: 563

Text #5

Max Range: 3.9231. Min Range: -3.9231

Max Act: 3.7980. Min Act: -0.1700

Data Index: 920804 (C4 (Web Text))

Max Activating Token Index: 194

Text #6

Max Range: 3.9231. Min Range: -3.9231

Max Act: 3.7980. Min Act: -0.1700

Data Index: 303359 (C4 (Web Text))

Max Activating Token Index: 576

Text #7

Max Range: 3.9231. Min Range: -3.9231

Max Act: 3.8293. Min Act: -0.1700

Data Index: 1153334 (C4 (Web Text))

Max Activating Token Index: 862

Text #8

Max Range: 3.9231. Min Range: -3.9231

Max Act: 3.7668. Min Act: -0.1700

Data Index: 220121 (C4 (Web Text))

Max Activating Token Index: 457

Text #9

Max Range: 3.9231. Min Range: -3.9231

Max Act: 3.7980. Min Act: -0.1700

Data Index: 166947 (C4 (Web Text))

Max Activating Token Index: 348

Text #10

Max Range: 3.9231. Min Range: -3.9231

Max Act: 3.7668. Min Act: -0.1700

Data Index: 392937 (C4 (Web Text))

Max Activating Token Index: 541

Text #11

Max Range: 3.9231. Min Range: -3.9231

Max Act: 3.7668. Min Act: -0.1700

Data Index: 1045474 (C4 (Web Text))

Max Activating Token Index: 277

Text #12

Max Range: 3.9231. Min Range: -3.9231

Max Act: 3.7668. Min Act: -0.1700

Data Index: 21939 (C4 (Web Text))

Max Activating Token Index: 172

Text #13

Max Range: 3.9231. Min Range: -3.9231

Max Act: 3.7668. Min Act: -0.1700

Data Index: 510511 (C4 (Web Text))

Max Activating Token Index: 653

Text #14

Max Range: 3.9231. Min Range: -3.9231

Max Act: 3.7355. Min Act: -0.1700

Data Index: 1203030 (C4 (Web Text))

Max Activating Token Index: 366

Text #15

Max Range: 3.9231. Min Range: -3.9231

Max Act: 3.7355. Min Act: -0.1700

Data Index: 306949 (C4 (Web Text))

Max Activating Token Index: 860

Text #16

Max Range: 3.9231. Min Range: -3.9231

Max Act: 3.7355. Min Act: -0.1700

Data Index: 368940 (C4 (Web Text))

Max Activating Token Index: 462

Text #17

Max Range: 3.9231. Min Range: -3.9231

Max Act: 3.7355. Min Act: -0.1700

Data Index: 588398 (C4 (Web Text))

Max Activating Token Index: 315

Text #18

Max Range: 3.9231. Min Range: -3.9231

Max Act: 3.7355. Min Act: -0.1700

Data Index: 163457 (C4 (Web Text))

Max Activating Token Index: 463

Text #19

Max Range: 3.9231. Min Range: -3.9231

Max Act: 3.7355. Min Act: -0.1700

Data Index: 36892 (C4 (Web Text))

Max Activating Token Index: 575