Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2212 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.8787. Min Range: -2.8787

Max Act: 2.8285. Min Act: -0.0000

Data Index: 801427 (C4 (Web Text))

Max Activating Token Index: 488

Text #1

Max Range: 2.8787. Min Range: -2.8787

Max Act: 2.7581. Min Act: -0.0000

Data Index: 1230091 (C4 (Web Text))

Max Activating Token Index: 695

Text #2

Max Range: 2.8787. Min Range: -2.8787

Max Act: 2.8787. Min Act: -0.0000

Data Index: 304791 (C4 (Web Text))

Max Activating Token Index: 970

Text #3

Max Range: 2.8787. Min Range: -2.8787

Max Act: 2.5932. Min Act: -0.0000

Data Index: 220314 (C4 (Web Text))

Max Activating Token Index: 835

Text #4

Max Range: 2.8787. Min Range: -2.8787

Max Act: 2.6557. Min Act: -0.0000

Data Index: 403447 (C4 (Web Text))

Max Activating Token Index: 327

Text #5

Max Range: 2.8787. Min Range: -2.8787

Max Act: 2.5582. Min Act: -0.0000

Data Index: 300803 (C4 (Web Text))

Max Activating Token Index: 1010

Text #6

Max Range: 2.8787. Min Range: -2.8787

Max Act: 2.5224. Min Act: -0.0000

Data Index: 957959 (C4 (Web Text))

Max Activating Token Index: 351

Text #7

Max Range: 2.8787. Min Range: -2.8787

Max Act: 2.6147. Min Act: -0.0000

Data Index: 1053999 (C4 (Web Text))

Max Activating Token Index: 972

Text #8

Max Range: 2.8787. Min Range: -2.8787

Max Act: 2.4114. Min Act: -0.0000

Data Index: 808379 (C4 (Web Text))

Max Activating Token Index: 661

Text #9

Max Range: 2.8787. Min Range: -2.8787

Max Act: 2.3763. Min Act: -0.0000

Data Index: 733561 (C4 (Web Text))

Max Activating Token Index: 995

Text #10

Max Range: 2.8787. Min Range: -2.8787

Max Act: 2.3854. Min Act: -0.0000

Data Index: 611482 (C4 (Web Text))

Max Activating Token Index: 595

Text #11

Max Range: 2.8787. Min Range: -2.8787

Max Act: 2.2187. Min Act: -0.0000

Data Index: 1042151 (C4 (Web Text))

Max Activating Token Index: 716

Text #12

Max Range: 2.8787. Min Range: -2.8787

Max Act: 2.1794. Min Act: -0.0000

Data Index: 362495 (C4 (Web Text))

Max Activating Token Index: 909

Text #13

Max Range: 2.8787. Min Range: -2.8787

Max Act: 2.3069. Min Act: -0.0000

Data Index: 172235 (C4 (Web Text))

Max Activating Token Index: 511

Text #14

Max Range: 2.8787. Min Range: -2.8787

Max Act: 2.2912. Min Act: -0.0000

Data Index: 1269738 (C4 (Web Text))

Max Activating Token Index: 374

Text #15

Max Range: 2.8787. Min Range: -2.8787

Max Act: 2.4108. Min Act: -0.0000

Data Index: 629511 (C4 (Web Text))

Max Activating Token Index: 9

Text #16

Max Range: 2.8787. Min Range: -2.8787

Max Act: 2.2773. Min Act: -0.0000

Data Index: 252939 (C4 (Web Text))

Max Activating Token Index: 594

Text #17

Max Range: 2.8787. Min Range: -2.8787

Max Act: 2.3334. Min Act: -0.0000

Data Index: 647954 (C4 (Web Text))

Max Activating Token Index: 585

Text #18

Max Range: 2.8787. Min Range: -2.8787

Max Act: 2.2071. Min Act: -0.0000

Data Index: 1243143 (C4 (Web Text))

Max Activating Token Index: 145

Text #19

Max Range: 2.8787. Min Range: -2.8787

Max Act: 2.3326. Min Act: -0.0000

Data Index: 871054 (C4 (Web Text))

Max Activating Token Index: 495