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

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

Neuron 2147 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: 0.9411. Min Range: -0.9411

Max Act: 0.9206. Min Act: -0.0000

Data Index: 116546 (C4 (Web Text))

Max Activating Token Index: 652

Text #1

Max Range: 0.9411. Min Range: -0.9411

Max Act: 0.8718. Min Act: -0.0000

Data Index: 334243 (C4 (Web Text))

Max Activating Token Index: 51

Text #2

Max Range: 0.9411. Min Range: -0.9411

Max Act: 0.8835. Min Act: -0.0000

Data Index: 1096953 (C4 (Web Text))

Max Activating Token Index: 423

Text #3

Max Range: 0.9411. Min Range: -0.9411

Max Act: 0.9411. Min Act: -0.0000

Data Index: 1219122 (C4 (Web Text))

Max Activating Token Index: 272

Text #4

Max Range: 0.9411. Min Range: -0.9411

Max Act: 0.9010. Min Act: -0.0000

Data Index: 298518 (C4 (Web Text))

Max Activating Token Index: 421

Text #5

Max Range: 0.9411. Min Range: -0.9411

Max Act: 0.8682. Min Act: -0.0000

Data Index: 864383 (C4 (Web Text))

Max Activating Token Index: 487

Text #6

Max Range: 0.9411. Min Range: -0.9411

Max Act: 0.8221. Min Act: -0.0000

Data Index: 1192762 (C4 (Web Text))

Max Activating Token Index: 627

Text #7

Max Range: 0.9411. Min Range: -0.9411

Max Act: 0.7473. Min Act: -0.0000

Data Index: 900129 (C4 (Web Text))

Max Activating Token Index: 470

Text #8

Max Range: 0.9411. Min Range: -0.9411

Max Act: 0.7871. Min Act: -0.0000

Data Index: 1100086 (C4 (Web Text))

Max Activating Token Index: 935

Text #9

Max Range: 0.9411. Min Range: -0.9411

Max Act: 0.7566. Min Act: -0.0000

Data Index: 1036373 (C4 (Web Text))

Max Activating Token Index: 824

Text #10

Max Range: 0.9411. Min Range: -0.9411

Max Act: 0.7189. Min Act: -0.0000

Data Index: 750204 (C4 (Web Text))

Max Activating Token Index: 231

Text #11

Max Range: 0.9411. Min Range: -0.9411

Max Act: 0.7030. Min Act: -0.0000

Data Index: 1060451 (C4 (Web Text))

Max Activating Token Index: 937

Text #12

Max Range: 0.9411. Min Range: -0.9411

Max Act: 0.7157. Min Act: -0.0000

Data Index: 280656 (C4 (Web Text))

Max Activating Token Index: 259

Text #13

Max Range: 0.9411. Min Range: -0.9411

Max Act: 0.6822. Min Act: -0.0000

Data Index: 615853 (C4 (Web Text))

Max Activating Token Index: 774

Text #14

Max Range: 0.9411. Min Range: -0.9411

Max Act: 0.6790. Min Act: -0.0000

Data Index: 291398 (C4 (Web Text))

Max Activating Token Index: 837

Text #15

Max Range: 0.9411. Min Range: -0.9411

Max Act: 0.6766. Min Act: -0.0000

Data Index: 883567 (C4 (Web Text))

Max Activating Token Index: 929

Text #16

Max Range: 0.9411. Min Range: -0.9411

Max Act: 0.6772. Min Act: -0.0000

Data Index: 482349 (C4 (Web Text))

Max Activating Token Index: 987

Text #17

Max Range: 0.9411. Min Range: -0.9411

Max Act: 0.6867. Min Act: -0.0000

Data Index: 693178 (C4 (Web Text))

Max Activating Token Index: 416

Text #18

Max Range: 0.9411. Min Range: -0.9411

Max Act: 0.7000. Min Act: -0.0000

Data Index: 21181 (C4 (Web Text))

Max Activating Token Index: 369

Text #19

Max Range: 0.9411. Min Range: -0.9411

Max Act: 0.6337. Min Act: -0.0000

Data Index: 1028878 (C4 (Web Text))

Max Activating Token Index: 409