Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4865 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.0103. Min Range: -1.0103

Max Act: 1.0103. Min Act: -0.0000

Data Index: 876277 (C4 (Web Text))

Max Activating Token Index: 634

Text #1

Max Range: 1.0103. Min Range: -1.0103

Max Act: 1.0075. Min Act: -0.0000

Data Index: 1332655 (C4 (Web Text))

Max Activating Token Index: 809

Text #2

Max Range: 1.0103. Min Range: -1.0103

Max Act: 0.9774. Min Act: -0.0000

Data Index: 1162719 (C4 (Web Text))

Max Activating Token Index: 279

Text #3

Max Range: 1.0103. Min Range: -1.0103

Max Act: 0.9284. Min Act: -0.0000

Data Index: 548576 (C4 (Web Text))

Max Activating Token Index: 607

Text #4

Max Range: 1.0103. Min Range: -1.0103

Max Act: 0.9227. Min Act: -0.0000

Data Index: 1321362 (C4 (Web Text))

Max Activating Token Index: 708

Text #5

Max Range: 1.0103. Min Range: -1.0103

Max Act: 0.8564. Min Act: -0.0000

Data Index: 862410 (C4 (Web Text))

Max Activating Token Index: 605

Text #6

Max Range: 1.0103. Min Range: -1.0103

Max Act: 0.9018. Min Act: -0.0000

Data Index: 1359657 (C4 (Web Text))

Max Activating Token Index: 336

Text #7

Max Range: 1.0103. Min Range: -1.0103

Max Act: 0.8394. Min Act: -0.0000

Data Index: 430163 (C4 (Web Text))

Max Activating Token Index: 85

Text #8

Max Range: 1.0103. Min Range: -1.0103

Max Act: 0.8795. Min Act: -0.0000

Data Index: 1246292 (C4 (Web Text))

Max Activating Token Index: 518

Text #9

Max Range: 1.0103. Min Range: -1.0103

Max Act: 0.8143. Min Act: -0.0000

Data Index: 545643 (C4 (Web Text))

Max Activating Token Index: 116

Text #10

Max Range: 1.0103. Min Range: -1.0103

Max Act: 0.8640. Min Act: -0.0000

Data Index: 201429 (C4 (Web Text))

Max Activating Token Index: 543

Text #11

Max Range: 1.0103. Min Range: -1.0103

Max Act: 0.8561. Min Act: -0.0000

Data Index: 176096 (C4 (Web Text))

Max Activating Token Index: 640

Text #12

Max Range: 1.0103. Min Range: -1.0103

Max Act: 0.8507. Min Act: -0.0000

Data Index: 653254 (C4 (Web Text))

Max Activating Token Index: 994

Text #13

Max Range: 1.0103. Min Range: -1.0103

Max Act: 0.8565. Min Act: -0.0000

Data Index: 182985 (C4 (Web Text))

Max Activating Token Index: 812

Text #14

Max Range: 1.0103. Min Range: -1.0103

Max Act: 0.8433. Min Act: -0.0000

Data Index: 611392 (C4 (Web Text))

Max Activating Token Index: 499

Text #15

Max Range: 1.0103. Min Range: -1.0103

Max Act: 0.8418. Min Act: -0.0000

Data Index: 573780 (C4 (Web Text))

Max Activating Token Index: 899

Text #16

Max Range: 1.0103. Min Range: -1.0103

Max Act: 0.8852. Min Act: -0.0000

Data Index: 871237 (C4 (Web Text))

Max Activating Token Index: 876

Text #17

Max Range: 1.0103. Min Range: -1.0103

Max Act: 0.8318. Min Act: -0.0000

Data Index: 657587 (C4 (Web Text))

Max Activating Token Index: 1002

Text #18

Max Range: 1.0103. Min Range: -1.0103

Max Act: 0.8296. Min Act: -0.0000

Data Index: 672842 (C4 (Web Text))

Max Activating Token Index: 412

Text #19

Max Range: 1.0103. Min Range: -1.0103

Max Act: 0.8234. Min Act: -0.0000

Data Index: 759450 (C4 (Web Text))

Max Activating Token Index: 196