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

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

Neuron 4640 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: 2.0585. Min Range: -2.0585

Max Act: 2.0549. Min Act: -0.0000

Data Index: 202659 (C4 (Web Text))

Max Activating Token Index: 607

Text #1

Max Range: 2.0585. Min Range: -2.0585

Max Act: 2.0376. Min Act: -0.0000

Data Index: 428805 (C4 (Web Text))

Max Activating Token Index: 720

Text #2

Max Range: 2.0585. Min Range: -2.0585

Max Act: 1.8919. Min Act: -0.0000

Data Index: 687286 (C4 (Web Text))

Max Activating Token Index: 399

Text #3

Max Range: 2.0585. Min Range: -2.0585

Max Act: 2.0585. Min Act: -0.0000

Data Index: 1283698 (C4 (Web Text))

Max Activating Token Index: 1001

Text #4

Max Range: 2.0585. Min Range: -2.0585

Max Act: 1.9643. Min Act: -0.0000

Data Index: 1173529 (C4 (Web Text))

Max Activating Token Index: 498

Text #5

Max Range: 2.0585. Min Range: -2.0585

Max Act: 1.9575. Min Act: -0.0000

Data Index: 262944 (C4 (Web Text))

Max Activating Token Index: 351

Text #6

Max Range: 2.0585. Min Range: -2.0585

Max Act: 1.9243. Min Act: -0.0000

Data Index: 329283 (C4 (Web Text))

Max Activating Token Index: 184

Text #7

Max Range: 2.0585. Min Range: -2.0585

Max Act: 1.9130. Min Act: -0.0000

Data Index: 1125816 (C4 (Web Text))

Max Activating Token Index: 189

Text #8

Max Range: 2.0585. Min Range: -2.0585

Max Act: 1.8207. Min Act: -0.0000

Data Index: 241348 (C4 (Web Text))

Max Activating Token Index: 883

Text #9

Max Range: 2.0585. Min Range: -2.0585

Max Act: 1.9005. Min Act: -0.0000

Data Index: 196550 (C4 (Web Text))

Max Activating Token Index: 146

Text #10

Max Range: 2.0585. Min Range: -2.0585

Max Act: 1.8922. Min Act: -0.0000

Data Index: 1247501 (C4 (Web Text))

Max Activating Token Index: 1003

Text #11

Max Range: 2.0585. Min Range: -2.0585

Max Act: 1.9848. Min Act: -0.0000

Data Index: 933659 (C4 (Web Text))

Max Activating Token Index: 927

Text #12

Max Range: 2.0585. Min Range: -2.0585

Max Act: 1.7839. Min Act: -0.0000

Data Index: 61193 (C4 (Web Text))

Max Activating Token Index: 341

Text #13

Max Range: 2.0585. Min Range: -2.0585

Max Act: 1.9726. Min Act: -0.0000

Data Index: 1332497 (C4 (Web Text))

Max Activating Token Index: 567

Text #14

Max Range: 2.0585. Min Range: -2.0585

Max Act: 1.8586. Min Act: -0.0000

Data Index: 1227461 (C4 (Web Text))

Max Activating Token Index: 909

Text #15

Max Range: 2.0585. Min Range: -2.0585

Max Act: 1.8605. Min Act: -0.0000

Data Index: 17420 (C4 (Web Text))

Max Activating Token Index: 939

Text #16

Max Range: 2.0585. Min Range: -2.0585

Max Act: 1.8608. Min Act: -0.0000

Data Index: 765854 (C4 (Web Text))

Max Activating Token Index: 799

Text #17

Max Range: 2.0585. Min Range: -2.0585

Max Act: 1.8565. Min Act: -0.0000

Data Index: 748803 (C4 (Web Text))

Max Activating Token Index: 691

Text #18

Max Range: 2.0585. Min Range: -2.0585

Max Act: 1.8459. Min Act: -0.0000

Data Index: 345566 (C4 (Web Text))

Max Activating Token Index: 548

Text #19

Max Range: 2.0585. Min Range: -2.0585

Max Act: 1.8687. Min Act: -0.0000

Data Index: 947575 (C4 (Web Text))

Max Activating Token Index: 89