Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1561 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.2665. Min Range: -3.2665

Max Act: 3.2665. Min Act: -0.1700

Data Index: 587793 (C4 (Web Text))

Max Activating Token Index: 314

Text #1

Max Range: 3.2665. Min Range: -3.2665

Max Act: 3.2508. Min Act: -0.1700

Data Index: 1174857 (C4 (Web Text))

Max Activating Token Index: 929

Text #2

Max Range: 3.2665. Min Range: -3.2665

Max Act: 3.2508. Min Act: -0.1700

Data Index: 115511 (C4 (Web Text))

Max Activating Token Index: 616

Text #3

Max Range: 3.2665. Min Range: -3.2665

Max Act: 3.2508. Min Act: -0.1700

Data Index: 1248069 (C4 (Web Text))

Max Activating Token Index: 813

Text #4

Max Range: 3.2665. Min Range: -3.2665

Max Act: 3.2508. Min Act: -0.1700

Data Index: 168851 (C4 (Web Text))

Max Activating Token Index: 730

Text #5

Max Range: 3.2665. Min Range: -3.2665

Max Act: 3.2508. Min Act: -0.1700

Data Index: 1211431 (C4 (Web Text))

Max Activating Token Index: 341

Text #6

Max Range: 3.2665. Min Range: -3.2665

Max Act: 3.2508. Min Act: -0.1700

Data Index: 90744 (C4 (Web Text))

Max Activating Token Index: 981

Text #7

Max Range: 3.2665. Min Range: -3.2665

Max Act: 3.2351. Min Act: -0.1700

Data Index: 543372 (C4 (Web Text))

Max Activating Token Index: 453

Text #8

Max Range: 3.2665. Min Range: -3.2665

Max Act: 3.2351. Min Act: -0.1700

Data Index: 587601 (C4 (Web Text))

Max Activating Token Index: 391

Text #9

Max Range: 3.2665. Min Range: -3.2665

Max Act: 3.2351. Min Act: -0.1700

Data Index: 212241 (C4 (Web Text))

Max Activating Token Index: 527

Text #10

Max Range: 3.2665. Min Range: -3.2665

Max Act: 3.2351. Min Act: -0.1700

Data Index: 573572 (C4 (Web Text))

Max Activating Token Index: 413

Text #11

Max Range: 3.2665. Min Range: -3.2665

Max Act: 3.2036. Min Act: -0.1700

Data Index: 1128861 (C4 (Web Text))

Max Activating Token Index: 806

Text #12

Max Range: 3.2665. Min Range: -3.2665

Max Act: 3.2036. Min Act: -0.1700

Data Index: 446213 (C4 (Web Text))

Max Activating Token Index: 939

Text #13

Max Range: 3.2665. Min Range: -3.2665

Max Act: 3.2351. Min Act: -0.1700

Data Index: 295282 (C4 (Web Text))

Max Activating Token Index: 109

Text #14

Max Range: 3.2665. Min Range: -3.2665

Max Act: 3.2194. Min Act: -0.1700

Data Index: 649173 (C4 (Web Text))

Max Activating Token Index: 912

Text #15

Max Range: 3.2665. Min Range: -3.2665

Max Act: 3.2351. Min Act: -0.1700

Data Index: 383910 (C4 (Web Text))

Max Activating Token Index: 673

Text #16

Max Range: 3.2665. Min Range: -3.2665

Max Act: 3.1879. Min Act: -0.1700

Data Index: 961596 (C4 (Web Text))

Max Activating Token Index: 546

Text #17

Max Range: 3.2665. Min Range: -3.2665

Max Act: 3.2351. Min Act: -0.1700

Data Index: 765248 (C4 (Web Text))

Max Activating Token Index: 1021

Text #18

Max Range: 3.2665. Min Range: -3.2665

Max Act: 3.1879. Min Act: -0.1700

Data Index: 1452379 (Python Code)

Max Activating Token Index: 706

Text #19

Max Range: 3.2665. Min Range: -3.2665

Max Act: 3.2036. Min Act: -0.1700

Data Index: 669774 (C4 (Web Text))

Max Activating Token Index: 782