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

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

Neuron 3408 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: 4.4879. Min Range: -4.4879

Max Act: 4.4879. Min Act: -0.0000

Data Index: 1069645 (C4 (Web Text))

Max Activating Token Index: 47

Text #1

Max Range: 4.4879. Min Range: -4.4879

Max Act: 3.7385. Min Act: -0.0000

Data Index: 667166 (C4 (Web Text))

Max Activating Token Index: 1012

Text #2

Max Range: 4.4879. Min Range: -4.4879

Max Act: 3.4554. Min Act: -0.0000

Data Index: 1028539 (C4 (Web Text))

Max Activating Token Index: 1019

Text #3

Max Range: 4.4879. Min Range: -4.4879

Max Act: 3.1667. Min Act: -0.0000

Data Index: 710635 (C4 (Web Text))

Max Activating Token Index: 473

Text #4

Max Range: 4.4879. Min Range: -4.4879

Max Act: 3.1236. Min Act: -0.0000

Data Index: 1050473 (C4 (Web Text))

Max Activating Token Index: 921

Text #5

Max Range: 4.4879. Min Range: -4.4879

Max Act: 3.1006. Min Act: -0.0000

Data Index: 319204 (C4 (Web Text))

Max Activating Token Index: 218

Text #6

Max Range: 4.4879. Min Range: -4.4879

Max Act: 2.7757. Min Act: -0.0000

Data Index: 623457 (C4 (Web Text))

Max Activating Token Index: 672

Text #7

Max Range: 4.4879. Min Range: -4.4879

Max Act: 2.8622. Min Act: -0.0000

Data Index: 75987 (C4 (Web Text))

Max Activating Token Index: 316

Text #8

Max Range: 4.4879. Min Range: -4.4879

Max Act: 2.8221. Min Act: -0.0000

Data Index: 1048804 (C4 (Web Text))

Max Activating Token Index: 142

Text #9

Max Range: 4.4879. Min Range: -4.4879

Max Act: 2.6592. Min Act: -0.0000

Data Index: 540664 (C4 (Web Text))

Max Activating Token Index: 1002

Text #10

Max Range: 4.4879. Min Range: -4.4879

Max Act: 2.8384. Min Act: -0.0000

Data Index: 1143769 (C4 (Web Text))

Max Activating Token Index: 666

Text #11

Max Range: 4.4879. Min Range: -4.4879

Max Act: 2.5737. Min Act: -0.0000

Data Index: 811868 (C4 (Web Text))

Max Activating Token Index: 872

Text #12

Max Range: 4.4879. Min Range: -4.4879

Max Act: 2.5345. Min Act: -0.0000

Data Index: 862482 (C4 (Web Text))

Max Activating Token Index: 292

Text #13

Max Range: 4.4879. Min Range: -4.4879

Max Act: 2.4839. Min Act: -0.0000

Data Index: 408490 (C4 (Web Text))

Max Activating Token Index: 339

Text #14

Max Range: 4.4879. Min Range: -4.4879

Max Act: 2.4626. Min Act: -0.0000

Data Index: 392473 (C4 (Web Text))

Max Activating Token Index: 334

Text #15

Max Range: 4.4879. Min Range: -4.4879

Max Act: 2.4562. Min Act: -0.0000

Data Index: 615319 (C4 (Web Text))

Max Activating Token Index: 649

Text #16

Max Range: 4.4879. Min Range: -4.4879

Max Act: 2.4160. Min Act: -0.0000

Data Index: 923507 (C4 (Web Text))

Max Activating Token Index: 189

Text #17

Max Range: 4.4879. Min Range: -4.4879

Max Act: 2.3538. Min Act: -0.0000

Data Index: 1297327 (C4 (Web Text))

Max Activating Token Index: 565

Text #18

Max Range: 4.4879. Min Range: -4.4879

Max Act: 2.3318. Min Act: -0.0000

Data Index: 1245364 (C4 (Web Text))

Max Activating Token Index: 398

Text #19

Max Range: 4.4879. Min Range: -4.4879

Max Act: 2.3324. Min Act: -0.0000

Data Index: 834391 (C4 (Web Text))

Max Activating Token Index: 459