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

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

Neuron 381 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.6639. Min Range: -5.6639

Max Act: 5.6639. Min Act: -0.0000

Data Index: 945397 (C4 (Web Text))

Max Activating Token Index: 56

Text #1

Max Range: 5.6639. Min Range: -5.6639

Max Act: 5.0234. Min Act: -0.0000

Data Index: 33681 (C4 (Web Text))

Max Activating Token Index: 706

Text #2

Max Range: 5.6639. Min Range: -5.6639

Max Act: 5.3060. Min Act: -0.0000

Data Index: 494915 (C4 (Web Text))

Max Activating Token Index: 104

Text #3

Max Range: 5.6639. Min Range: -5.6639

Max Act: 5.4473. Min Act: -0.0000

Data Index: 1303468 (C4 (Web Text))

Max Activating Token Index: 536

Text #4

Max Range: 5.6639. Min Range: -5.6639

Max Act: 5.2168. Min Act: -0.0000

Data Index: 273561 (C4 (Web Text))

Max Activating Token Index: 517

Text #5

Max Range: 5.6639. Min Range: -5.6639

Max Act: 4.3877. Min Act: -0.0000

Data Index: 1305520 (C4 (Web Text))

Max Activating Token Index: 73

Text #6

Max Range: 5.6639. Min Range: -5.6639

Max Act: 4.1661. Min Act: -0.0000

Data Index: 1053866 (C4 (Web Text))

Max Activating Token Index: 216

Text #7

Max Range: 5.6639. Min Range: -5.6639

Max Act: 4.3987. Min Act: -0.0000

Data Index: 357452 (C4 (Web Text))

Max Activating Token Index: 235

Text #8

Max Range: 5.6639. Min Range: -5.6639

Max Act: 3.5877. Min Act: -0.0000

Data Index: 1236051 (C4 (Web Text))

Max Activating Token Index: 143

Text #9

Max Range: 5.6639. Min Range: -5.6639

Max Act: 4.1290. Min Act: -0.0000

Data Index: 1244921 (C4 (Web Text))

Max Activating Token Index: 390

Text #10

Max Range: 5.6639. Min Range: -5.6639

Max Act: 3.9125. Min Act: -0.0000

Data Index: 327690 (C4 (Web Text))

Max Activating Token Index: 477

Text #11

Max Range: 5.6639. Min Range: -5.6639

Max Act: 4.2329. Min Act: -0.0000

Data Index: 304848 (C4 (Web Text))

Max Activating Token Index: 492

Text #12

Max Range: 5.6639. Min Range: -5.6639

Max Act: 3.8385. Min Act: -0.0000

Data Index: 366991 (C4 (Web Text))

Max Activating Token Index: 147

Text #13

Max Range: 5.6639. Min Range: -5.6639

Max Act: 3.8265. Min Act: -0.0000

Data Index: 1028270 (C4 (Web Text))

Max Activating Token Index: 92

Text #14

Max Range: 5.6639. Min Range: -5.6639

Max Act: 3.9533. Min Act: -0.0000

Data Index: 1357339 (C4 (Web Text))

Max Activating Token Index: 33

Text #15

Max Range: 5.6639. Min Range: -5.6639

Max Act: 3.9105. Min Act: -0.0000

Data Index: 542918 (C4 (Web Text))

Max Activating Token Index: 402

Text #16

Max Range: 5.6639. Min Range: -5.6639

Max Act: 3.8942. Min Act: -0.0000

Data Index: 1058759 (C4 (Web Text))

Max Activating Token Index: 657

Text #17

Max Range: 5.6639. Min Range: -5.6639

Max Act: 3.8571. Min Act: -0.0000

Data Index: 903798 (C4 (Web Text))

Max Activating Token Index: 472

Text #18

Max Range: 5.6639. Min Range: -5.6639

Max Act: 3.8618. Min Act: -0.0000

Data Index: 154965 (C4 (Web Text))

Max Activating Token Index: 582

Text #19

Max Range: 5.6639. Min Range: -5.6639

Max Act: 3.8378. Min Act: -0.0000

Data Index: 894459 (C4 (Web Text))

Max Activating Token Index: 380