Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 358 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.6240. Min Range: -0.6240

Max Act: 0.6240. Min Act: -0.0000

Data Index: 276026 (C4 (Web Text))

Max Activating Token Index: 434

Text #1

Max Range: 0.6240. Min Range: -0.6240

Max Act: 0.4882. Min Act: -0.0000

Data Index: 488788 (C4 (Web Text))

Max Activating Token Index: 231

Text #2

Max Range: 0.6240. Min Range: -0.6240

Max Act: 0.4721. Min Act: -0.0000

Data Index: 202956 (C4 (Web Text))

Max Activating Token Index: 621

Text #3

Max Range: 0.6240. Min Range: -0.6240

Max Act: 0.4142. Min Act: -0.0000

Data Index: 114921 (C4 (Web Text))

Max Activating Token Index: 628

Text #4

Max Range: 0.6240. Min Range: -0.6240

Max Act: 0.4072. Min Act: -0.0000

Data Index: 366841 (C4 (Web Text))

Max Activating Token Index: 7

Text #5

Max Range: 0.6240. Min Range: -0.6240

Max Act: 0.4150. Min Act: -0.0000

Data Index: 916886 (C4 (Web Text))

Max Activating Token Index: 17

Text #6

Max Range: 0.6240. Min Range: -0.6240

Max Act: 0.4093. Min Act: -0.0000

Data Index: 282540 (C4 (Web Text))

Max Activating Token Index: 796

Text #7

Max Range: 0.6240. Min Range: -0.6240

Max Act: 0.4052. Min Act: -0.0000

Data Index: 999695 (C4 (Web Text))

Max Activating Token Index: 518

Text #8

Max Range: 0.6240. Min Range: -0.6240

Max Act: 0.3747. Min Act: -0.0000

Data Index: 1311601 (C4 (Web Text))

Max Activating Token Index: 743

Text #9

Max Range: 0.6240. Min Range: -0.6240

Max Act: 0.3425. Min Act: -0.0000

Data Index: 945428 (C4 (Web Text))

Max Activating Token Index: 892

Text #10

Max Range: 0.6240. Min Range: -0.6240

Max Act: 0.3861. Min Act: -0.0000

Data Index: 271468 (C4 (Web Text))

Max Activating Token Index: 714

Text #11

Max Range: 0.6240. Min Range: -0.6240

Max Act: 0.3792. Min Act: -0.0001

Data Index: 435015 (C4 (Web Text))

Max Activating Token Index: 467

Text #12

Max Range: 0.6240. Min Range: -0.6240

Max Act: 0.3682. Min Act: -0.0000

Data Index: 616500 (C4 (Web Text))

Max Activating Token Index: 846

Text #13

Max Range: 0.6240. Min Range: -0.6240

Max Act: 0.3553. Min Act: -0.0000

Data Index: 628870 (C4 (Web Text))

Max Activating Token Index: 703

Text #14

Max Range: 0.6240. Min Range: -0.6240

Max Act: 0.3541. Min Act: -0.0000

Data Index: 1045791 (C4 (Web Text))

Max Activating Token Index: 685

Text #15

Max Range: 0.6240. Min Range: -0.6240

Max Act: 0.3636. Min Act: -0.0000

Data Index: 992309 (C4 (Web Text))

Max Activating Token Index: 490

Text #16

Max Range: 0.6240. Min Range: -0.6240

Max Act: 0.3607. Min Act: -0.0001

Data Index: 902339 (C4 (Web Text))

Max Activating Token Index: 123

Text #17

Max Range: 0.6240. Min Range: -0.6240

Max Act: 0.3445. Min Act: -0.0000

Data Index: 433691 (C4 (Web Text))

Max Activating Token Index: 930

Text #18

Max Range: 0.6240. Min Range: -0.6240

Max Act: 0.3755. Min Act: -0.0000

Data Index: 356331 (C4 (Web Text))

Max Activating Token Index: 556

Text #19

Max Range: 0.6240. Min Range: -0.6240

Max Act: 0.3453. Min Act: -0.0000

Data Index: 747048 (C4 (Web Text))

Max Activating Token Index: 176