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

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

Neuron 1561 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2878. Min Range: -0.2878

Max Act: 0.2771. Min Act: -0.0000

Data Index: 788226 (C4 (Web Text))

Max Activating Token Index: 315

Text #1

Max Range: 0.2878. Min Range: -0.2878

Max Act: 0.2878. Min Act: -0.0000

Data Index: 367940 (C4 (Web Text))

Max Activating Token Index: 781

Text #2

Max Range: 0.2878. Min Range: -0.2878

Max Act: 0.2615. Min Act: -0.0000

Data Index: 1120313 (C4 (Web Text))

Max Activating Token Index: 940

Text #3

Max Range: 0.2878. Min Range: -0.2878

Max Act: 0.2620. Min Act: -0.0000

Data Index: 429121 (C4 (Web Text))

Max Activating Token Index: 47

Text #4

Max Range: 0.2878. Min Range: -0.2878

Max Act: 0.2574. Min Act: -0.0000

Data Index: 129145 (C4 (Web Text))

Max Activating Token Index: 20

Text #5

Max Range: 0.2878. Min Range: -0.2878

Max Act: 0.2301. Min Act: -0.0000

Data Index: 1127369 (C4 (Web Text))

Max Activating Token Index: 724

Text #6

Max Range: 0.2878. Min Range: -0.2878

Max Act: 0.2283. Min Act: -0.0000

Data Index: 1268640 (C4 (Web Text))

Max Activating Token Index: 770

Text #7

Max Range: 0.2878. Min Range: -0.2878

Max Act: 0.2570. Min Act: -0.0000

Data Index: 725032 (C4 (Web Text))

Max Activating Token Index: 397

Text #8

Max Range: 0.2878. Min Range: -0.2878

Max Act: 0.2260. Min Act: -0.0000

Data Index: 435206 (C4 (Web Text))

Max Activating Token Index: 595

Text #9

Max Range: 0.2878. Min Range: -0.2878

Max Act: 0.2211. Min Act: -0.0000

Data Index: 400729 (C4 (Web Text))

Max Activating Token Index: 347

Text #10

Max Range: 0.2878. Min Range: -0.2878

Max Act: 0.2270. Min Act: -0.0000

Data Index: 117024 (C4 (Web Text))

Max Activating Token Index: 221

Text #11

Max Range: 0.2878. Min Range: -0.2878

Max Act: 0.2235. Min Act: -0.0000

Data Index: 1097067 (C4 (Web Text))

Max Activating Token Index: 163

Text #12

Max Range: 0.2878. Min Range: -0.2878

Max Act: 0.2118. Min Act: -0.0000

Data Index: 374393 (C4 (Web Text))

Max Activating Token Index: 711

Text #13

Max Range: 0.2878. Min Range: -0.2878

Max Act: 0.2047. Min Act: -0.0000

Data Index: 1078871 (C4 (Web Text))

Max Activating Token Index: 782

Text #14

Max Range: 0.2878. Min Range: -0.2878

Max Act: 0.2293. Min Act: -0.0000

Data Index: 87131 (C4 (Web Text))

Max Activating Token Index: 395

Text #15

Max Range: 0.2878. Min Range: -0.2878

Max Act: 0.2123. Min Act: -0.0000

Data Index: 1459345 (Python Code)

Max Activating Token Index: 143

Text #16

Max Range: 0.2878. Min Range: -0.2878

Max Act: 0.1939. Min Act: -0.0000

Data Index: 934784 (C4 (Web Text))

Max Activating Token Index: 843

Text #17

Max Range: 0.2878. Min Range: -0.2878

Max Act: 0.1994. Min Act: -0.0000

Data Index: 943447 (C4 (Web Text))

Max Activating Token Index: 246

Text #18

Max Range: 0.2878. Min Range: -0.2878

Max Act: 0.2130. Min Act: -0.0000

Data Index: 1397241 (Python Code)

Max Activating Token Index: 309

Text #19

Max Range: 0.2878. Min Range: -0.2878

Max Act: 0.2049. Min Act: -0.0000

Data Index: 1089423 (C4 (Web Text))

Max Activating Token Index: 292