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

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

Neuron 1797 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.7698. Min Range: -5.7698

Max Act: 5.7698. Min Act: -0.0000

Data Index: 268569 (C4 (Web Text))

Max Activating Token Index: 353

Text #1

Max Range: 5.7698. Min Range: -5.7698

Max Act: 5.3948. Min Act: -0.0000

Data Index: 201258 (C4 (Web Text))

Max Activating Token Index: 807

Text #2

Max Range: 5.7698. Min Range: -5.7698

Max Act: 5.2666. Min Act: -0.0000

Data Index: 1065922 (C4 (Web Text))

Max Activating Token Index: 456

Text #3

Max Range: 5.7698. Min Range: -5.7698

Max Act: 5.1322. Min Act: -0.0000

Data Index: 377225 (C4 (Web Text))

Max Activating Token Index: 906

Text #4

Max Range: 5.7698. Min Range: -5.7698

Max Act: 5.0722. Min Act: -0.0000

Data Index: 466421 (C4 (Web Text))

Max Activating Token Index: 539

Text #5

Max Range: 5.7698. Min Range: -5.7698

Max Act: 5.2612. Min Act: -0.0000

Data Index: 1132324 (C4 (Web Text))

Max Activating Token Index: 832

Text #6

Max Range: 5.7698. Min Range: -5.7698

Max Act: 4.9454. Min Act: -0.0000

Data Index: 1008315 (C4 (Web Text))

Max Activating Token Index: 545

Text #7

Max Range: 5.7698. Min Range: -5.7698

Max Act: 5.0868. Min Act: -0.0000

Data Index: 520664 (C4 (Web Text))

Max Activating Token Index: 949

Text #8

Max Range: 5.7698. Min Range: -5.7698

Max Act: 4.9117. Min Act: -0.0000

Data Index: 414816 (C4 (Web Text))

Max Activating Token Index: 283

Text #9

Max Range: 5.7698. Min Range: -5.7698

Max Act: 4.7434. Min Act: -0.0000

Data Index: 186203 (C4 (Web Text))

Max Activating Token Index: 543

Text #10

Max Range: 5.7698. Min Range: -5.7698

Max Act: 4.8440. Min Act: -0.0000

Data Index: 240713 (C4 (Web Text))

Max Activating Token Index: 681

Text #11

Max Range: 5.7698. Min Range: -5.7698

Max Act: 4.6870. Min Act: -0.0000

Data Index: 955491 (C4 (Web Text))

Max Activating Token Index: 19

Text #12

Max Range: 5.7698. Min Range: -5.7698

Max Act: 4.8921. Min Act: -0.0000

Data Index: 338532 (C4 (Web Text))

Max Activating Token Index: 677

Text #13

Max Range: 5.7698. Min Range: -5.7698

Max Act: 4.6291. Min Act: -0.0000

Data Index: 1057246 (C4 (Web Text))

Max Activating Token Index: 826

Text #14

Max Range: 5.7698. Min Range: -5.7698

Max Act: 4.5886. Min Act: -0.0000

Data Index: 413725 (C4 (Web Text))

Max Activating Token Index: 846

Text #15

Max Range: 5.7698. Min Range: -5.7698

Max Act: 4.6315. Min Act: -0.0000

Data Index: 1159110 (C4 (Web Text))

Max Activating Token Index: 943

Text #16

Max Range: 5.7698. Min Range: -5.7698

Max Act: 4.6645. Min Act: -0.0000

Data Index: 739994 (C4 (Web Text))

Max Activating Token Index: 894

Text #17

Max Range: 5.7698. Min Range: -5.7698

Max Act: 4.5677. Min Act: -0.0000

Data Index: 944439 (C4 (Web Text))

Max Activating Token Index: 619

Text #18

Max Range: 5.7698. Min Range: -5.7698

Max Act: 4.1969. Min Act: -0.0000

Data Index: 889737 (C4 (Web Text))

Max Activating Token Index: 156

Text #19

Max Range: 5.7698. Min Range: -5.7698

Max Act: 4.6688. Min Act: -0.0000

Data Index: 604048 (C4 (Web Text))

Max Activating Token Index: 841