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

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

Neuron 1650 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: 3.6411. Min Range: -3.6411

Max Act: 3.6411. Min Act: -0.1700

Data Index: 1356461 (C4 (Web Text))

Max Activating Token Index: 858

Text #1

Max Range: 3.6411. Min Range: -3.6411

Max Act: 3.6098. Min Act: -0.1700

Data Index: 406118 (C4 (Web Text))

Max Activating Token Index: 815

Text #2

Max Range: 3.6411. Min Range: -3.6411

Max Act: 3.5628. Min Act: -0.1700

Data Index: 1171285 (C4 (Web Text))

Max Activating Token Index: 171

Text #3

Max Range: 3.6411. Min Range: -3.6411

Max Act: 3.5471. Min Act: -0.1700

Data Index: 1010578 (C4 (Web Text))

Max Activating Token Index: 144

Text #4

Max Range: 3.6411. Min Range: -3.6411

Max Act: 3.5471. Min Act: -0.1700

Data Index: 644670 (C4 (Web Text))

Max Activating Token Index: 180

Text #5

Max Range: 3.6411. Min Range: -3.6411

Max Act: 3.5471. Min Act: -0.1700

Data Index: 622430 (C4 (Web Text))

Max Activating Token Index: 32

Text #6

Max Range: 3.6411. Min Range: -3.6411

Max Act: 3.5315. Min Act: -0.1700

Data Index: 699121 (C4 (Web Text))

Max Activating Token Index: 903

Text #7

Max Range: 3.6411. Min Range: -3.6411

Max Act: 3.5315. Min Act: -0.1700

Data Index: 628448 (C4 (Web Text))

Max Activating Token Index: 555

Text #8

Max Range: 3.6411. Min Range: -3.6411

Max Act: 3.5315. Min Act: -0.1700

Data Index: 491202 (C4 (Web Text))

Max Activating Token Index: 886

Text #9

Max Range: 3.6411. Min Range: -3.6411

Max Act: 3.5315. Min Act: -0.1700

Data Index: 591192 (C4 (Web Text))

Max Activating Token Index: 521

Text #10

Max Range: 3.6411. Min Range: -3.6411

Max Act: 3.5001. Min Act: -0.1700

Data Index: 387406 (C4 (Web Text))

Max Activating Token Index: 234

Text #11

Max Range: 3.6411. Min Range: -3.6411

Max Act: 3.5158. Min Act: -0.1700

Data Index: 78641 (C4 (Web Text))

Max Activating Token Index: 964

Text #12

Max Range: 3.6411. Min Range: -3.6411

Max Act: 3.5001. Min Act: -0.1700

Data Index: 707282 (C4 (Web Text))

Max Activating Token Index: 971

Text #13

Max Range: 3.6411. Min Range: -3.6411

Max Act: 3.5001. Min Act: -0.1700

Data Index: 61356 (C4 (Web Text))

Max Activating Token Index: 704

Text #14

Max Range: 3.6411. Min Range: -3.6411

Max Act: 3.5001. Min Act: -0.1700

Data Index: 967608 (C4 (Web Text))

Max Activating Token Index: 768

Text #15

Max Range: 3.6411. Min Range: -3.6411

Max Act: 3.4845. Min Act: -0.1700

Data Index: 699162 (C4 (Web Text))

Max Activating Token Index: 877

Text #16

Max Range: 3.6411. Min Range: -3.6411

Max Act: 3.4688. Min Act: -0.1700

Data Index: 660599 (C4 (Web Text))

Max Activating Token Index: 723

Text #17

Max Range: 3.6411. Min Range: -3.6411

Max Act: 3.4845. Min Act: -0.1700

Data Index: 99281 (C4 (Web Text))

Max Activating Token Index: 318

Text #18

Max Range: 3.6411. Min Range: -3.6411

Max Act: 3.4688. Min Act: -0.1700

Data Index: 852072 (C4 (Web Text))

Max Activating Token Index: 75

Text #19

Max Range: 3.6411. Min Range: -3.6411

Max Act: 3.4845. Min Act: -0.1700

Data Index: 990094 (C4 (Web Text))

Max Activating Token Index: 712