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

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

Neuron 3718 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: 4.5169. Min Range: -4.5169

Max Act: 4.5169. Min Act: -0.0000

Data Index: 83875 (C4 (Web Text))

Max Activating Token Index: 301

Text #1

Max Range: 4.5169. Min Range: -4.5169

Max Act: 4.3118. Min Act: -0.0000

Data Index: 886589 (C4 (Web Text))

Max Activating Token Index: 749

Text #2

Max Range: 4.5169. Min Range: -4.5169

Max Act: 4.2293. Min Act: -0.0000

Data Index: 682639 (C4 (Web Text))

Max Activating Token Index: 397

Text #3

Max Range: 4.5169. Min Range: -4.5169

Max Act: 4.2807. Min Act: -0.0000

Data Index: 650918 (C4 (Web Text))

Max Activating Token Index: 268

Text #4

Max Range: 4.5169. Min Range: -4.5169

Max Act: 4.0589. Min Act: -0.0000

Data Index: 1039201 (C4 (Web Text))

Max Activating Token Index: 393

Text #5

Max Range: 4.5169. Min Range: -4.5169

Max Act: 3.9873. Min Act: -0.0000

Data Index: 398969 (C4 (Web Text))

Max Activating Token Index: 716

Text #6

Max Range: 4.5169. Min Range: -4.5169

Max Act: 3.6912. Min Act: -0.0000

Data Index: 971794 (C4 (Web Text))

Max Activating Token Index: 440

Text #7

Max Range: 4.5169. Min Range: -4.5169

Max Act: 3.6399. Min Act: -0.0000

Data Index: 1215448 (C4 (Web Text))

Max Activating Token Index: 929

Text #8

Max Range: 4.5169. Min Range: -4.5169

Max Act: 3.3032. Min Act: -0.0000

Data Index: 799849 (C4 (Web Text))

Max Activating Token Index: 953

Text #9

Max Range: 4.5169. Min Range: -4.5169

Max Act: 3.7835. Min Act: -0.0000

Data Index: 1040812 (C4 (Web Text))

Max Activating Token Index: 507

Text #10

Max Range: 4.5169. Min Range: -4.5169

Max Act: 3.2568. Min Act: -0.0000

Data Index: 440294 (C4 (Web Text))

Max Activating Token Index: 867

Text #11

Max Range: 4.5169. Min Range: -4.5169

Max Act: 3.1680. Min Act: -0.0000

Data Index: 789060 (C4 (Web Text))

Max Activating Token Index: 670

Text #12

Max Range: 4.5169. Min Range: -4.5169

Max Act: 3.3310. Min Act: -0.0000

Data Index: 568540 (C4 (Web Text))

Max Activating Token Index: 763

Text #13

Max Range: 4.5169. Min Range: -4.5169

Max Act: 3.3333. Min Act: -0.0000

Data Index: 515667 (C4 (Web Text))

Max Activating Token Index: 509

Text #14

Max Range: 4.5169. Min Range: -4.5169

Max Act: 3.4673. Min Act: -0.0000

Data Index: 1079075 (C4 (Web Text))

Max Activating Token Index: 658

Text #15

Max Range: 4.5169. Min Range: -4.5169

Max Act: 2.5154. Min Act: -0.0000

Data Index: 870360 (C4 (Web Text))

Max Activating Token Index: 604

Text #16

Max Range: 4.5169. Min Range: -4.5169

Max Act: 3.1272. Min Act: -0.0000

Data Index: 344252 (C4 (Web Text))

Max Activating Token Index: 1012

Text #17

Max Range: 4.5169. Min Range: -4.5169

Max Act: 3.2428. Min Act: -0.0000

Data Index: 789534 (C4 (Web Text))

Max Activating Token Index: 495

Text #18

Max Range: 4.5169. Min Range: -4.5169

Max Act: 3.2103. Min Act: -0.0000

Data Index: 28696 (C4 (Web Text))

Max Activating Token Index: 552

Text #19

Max Range: 4.5169. Min Range: -4.5169

Max Act: 3.2228. Min Act: -0.0000

Data Index: 260305 (C4 (Web Text))

Max Activating Token Index: 817