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

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

Neuron 3347 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: 0.5385. Min Range: -0.5385

Max Act: 0.5385. Min Act: -0.0000

Data Index: 553432 (C4 (Web Text))

Max Activating Token Index: 503

Text #1

Max Range: 0.5385. Min Range: -0.5385

Max Act: 0.4614. Min Act: -0.0000

Data Index: 160237 (C4 (Web Text))

Max Activating Token Index: 292

Text #2

Max Range: 0.5385. Min Range: -0.5385

Max Act: 0.4233. Min Act: -0.0000

Data Index: 63339 (C4 (Web Text))

Max Activating Token Index: 975

Text #3

Max Range: 0.5385. Min Range: -0.5385

Max Act: 0.4687. Min Act: -0.0000

Data Index: 320316 (C4 (Web Text))

Max Activating Token Index: 88

Text #4

Max Range: 0.5385. Min Range: -0.5385

Max Act: 0.4493. Min Act: -0.0000

Data Index: 444025 (C4 (Web Text))

Max Activating Token Index: 883

Text #5

Max Range: 0.5385. Min Range: -0.5385

Max Act: 0.4425. Min Act: -0.0000

Data Index: 540698 (C4 (Web Text))

Max Activating Token Index: 938

Text #6

Max Range: 0.5385. Min Range: -0.5385

Max Act: 0.4313. Min Act: -0.0000

Data Index: 481635 (C4 (Web Text))

Max Activating Token Index: 85

Text #7

Max Range: 0.5385. Min Range: -0.5385

Max Act: 0.4452. Min Act: -0.0000

Data Index: 833969 (C4 (Web Text))

Max Activating Token Index: 912

Text #8

Max Range: 0.5385. Min Range: -0.5385

Max Act: 0.4382. Min Act: -0.0000

Data Index: 310701 (C4 (Web Text))

Max Activating Token Index: 183

Text #9

Max Range: 0.5385. Min Range: -0.5385

Max Act: 0.3568. Min Act: -0.0000

Data Index: 148541 (C4 (Web Text))

Max Activating Token Index: 610

Text #10

Max Range: 0.5385. Min Range: -0.5385

Max Act: 0.4333. Min Act: -0.0000

Data Index: 295103 (C4 (Web Text))

Max Activating Token Index: 70

Text #11

Max Range: 0.5385. Min Range: -0.5385

Max Act: 0.4020. Min Act: -0.0000

Data Index: 452918 (C4 (Web Text))

Max Activating Token Index: 122

Text #12

Max Range: 0.5385. Min Range: -0.5385

Max Act: 0.3830. Min Act: -0.0000

Data Index: 1029696 (C4 (Web Text))

Max Activating Token Index: 611

Text #13

Max Range: 0.5385. Min Range: -0.5385

Max Act: 0.4054. Min Act: -0.0000

Data Index: 998194 (C4 (Web Text))

Max Activating Token Index: 725

Text #14

Max Range: 0.5385. Min Range: -0.5385

Max Act: 0.4052. Min Act: -0.0000

Data Index: 730356 (C4 (Web Text))

Max Activating Token Index: 584

Text #15

Max Range: 0.5385. Min Range: -0.5385

Max Act: 0.4158. Min Act: -0.0000

Data Index: 1031974 (C4 (Web Text))

Max Activating Token Index: 153

Text #16

Max Range: 0.5385. Min Range: -0.5385

Max Act: 0.4027. Min Act: -0.0000

Data Index: 650337 (C4 (Web Text))

Max Activating Token Index: 494

Text #17

Max Range: 0.5385. Min Range: -0.5385

Max Act: 0.3976. Min Act: -0.0000

Data Index: 1116464 (C4 (Web Text))

Max Activating Token Index: 420

Text #18

Max Range: 0.5385. Min Range: -0.5385

Max Act: 0.3732. Min Act: -0.0000

Data Index: 412625 (C4 (Web Text))

Max Activating Token Index: 476

Text #19

Max Range: 0.5385. Min Range: -0.5385

Max Act: 0.3820. Min Act: -0.0000

Data Index: 261998 (C4 (Web Text))

Max Activating Token Index: 810