Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4407 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.0189. Min Range: -3.0189

Max Act: 3.0189. Min Act: -0.0001

Data Index: 814689 (C4 (Web Text))

Max Activating Token Index: 880

Text #1

Max Range: 3.0189. Min Range: -3.0189

Max Act: 2.8778. Min Act: -0.0001

Data Index: 1279610 (C4 (Web Text))

Max Activating Token Index: 880

Text #2

Max Range: 3.0189. Min Range: -3.0189

Max Act: 2.1500. Min Act: -0.0001

Data Index: 973445 (C4 (Web Text))

Max Activating Token Index: 827

Text #3

Max Range: 3.0189. Min Range: -3.0189

Max Act: 2.7057. Min Act: -0.0001

Data Index: 270727 (C4 (Web Text))

Max Activating Token Index: 747

Text #4

Max Range: 3.0189. Min Range: -3.0189

Max Act: 2.8933. Min Act: -0.0002

Data Index: 1300051 (C4 (Web Text))

Max Activating Token Index: 869

Text #5

Max Range: 3.0189. Min Range: -3.0189

Max Act: 2.6128. Min Act: -0.0001

Data Index: 690165 (C4 (Web Text))

Max Activating Token Index: 280

Text #6

Max Range: 3.0189. Min Range: -3.0189

Max Act: 2.6998. Min Act: -0.0001

Data Index: 1329056 (C4 (Web Text))

Max Activating Token Index: 1007

Text #7

Max Range: 3.0189. Min Range: -3.0189

Max Act: 2.9365. Min Act: -0.0001

Data Index: 563906 (C4 (Web Text))

Max Activating Token Index: 861

Text #8

Max Range: 3.0189. Min Range: -3.0189

Max Act: 2.5435. Min Act: -0.0001

Data Index: 521236 (C4 (Web Text))

Max Activating Token Index: 1014

Text #9

Max Range: 3.0189. Min Range: -3.0189

Max Act: 2.7572. Min Act: -0.0001

Data Index: 1057164 (C4 (Web Text))

Max Activating Token Index: 855

Text #10

Max Range: 3.0189. Min Range: -3.0189

Max Act: 2.3990. Min Act: -0.0001

Data Index: 175206 (C4 (Web Text))

Max Activating Token Index: 438

Text #11

Max Range: 3.0189. Min Range: -3.0189

Max Act: 2.5419. Min Act: -0.0001

Data Index: 767759 (C4 (Web Text))

Max Activating Token Index: 905

Text #12

Max Range: 3.0189. Min Range: -3.0189

Max Act: 2.6464. Min Act: -0.0002

Data Index: 453292 (C4 (Web Text))

Max Activating Token Index: 729

Text #13

Max Range: 3.0189. Min Range: -3.0189

Max Act: 2.5264. Min Act: -0.0001

Data Index: 453554 (C4 (Web Text))

Max Activating Token Index: 930

Text #14

Max Range: 3.0189. Min Range: -3.0189

Max Act: 2.5349. Min Act: -0.0001

Data Index: 183694 (C4 (Web Text))

Max Activating Token Index: 976

Text #15

Max Range: 3.0189. Min Range: -3.0189

Max Act: 2.7392. Min Act: -0.0001

Data Index: 191016 (C4 (Web Text))

Max Activating Token Index: 93

Text #16

Max Range: 3.0189. Min Range: -3.0189

Max Act: 2.8077. Min Act: -0.0001

Data Index: 1325622 (C4 (Web Text))

Max Activating Token Index: 874

Text #17

Max Range: 3.0189. Min Range: -3.0189

Max Act: 2.5808. Min Act: -0.0001

Data Index: 884309 (C4 (Web Text))

Max Activating Token Index: 973

Text #18

Max Range: 3.0189. Min Range: -3.0189

Max Act: 2.5690. Min Act: -0.0001

Data Index: 436491 (C4 (Web Text))

Max Activating Token Index: 684

Text #19

Max Range: 3.0189. Min Range: -3.0189

Max Act: 2.7936. Min Act: -0.0001

Data Index: 1220139 (C4 (Web Text))

Max Activating Token Index: 763