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

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

Neuron 3233 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: 0.3364. Min Range: -0.3364

Max Act: 0.3190. Min Act: -0.0000

Data Index: 1009185 (C4 (Web Text))

Max Activating Token Index: 162

Text #1

Max Range: 0.3364. Min Range: -0.3364

Max Act: 0.3364. Min Act: -0.0000

Data Index: 981879 (C4 (Web Text))

Max Activating Token Index: 181

Text #2

Max Range: 0.3364. Min Range: -0.3364

Max Act: 0.3267. Min Act: -0.0000

Data Index: 508590 (C4 (Web Text))

Max Activating Token Index: 208

Text #3

Max Range: 0.3364. Min Range: -0.3364

Max Act: 0.3128. Min Act: -0.0000

Data Index: 343324 (C4 (Web Text))

Max Activating Token Index: 425

Text #4

Max Range: 0.3364. Min Range: -0.3364

Max Act: 0.2962. Min Act: -0.0000

Data Index: 1029541 (C4 (Web Text))

Max Activating Token Index: 614

Text #5

Max Range: 0.3364. Min Range: -0.3364

Max Act: 0.2517. Min Act: -0.0000

Data Index: 151284 (C4 (Web Text))

Max Activating Token Index: 911

Text #6

Max Range: 0.3364. Min Range: -0.3364

Max Act: 0.1971. Min Act: -0.0000

Data Index: 413947 (C4 (Web Text))

Max Activating Token Index: 380

Text #7

Max Range: 0.3364. Min Range: -0.3364

Max Act: 0.2235. Min Act: -0.0000

Data Index: 13694 (C4 (Web Text))

Max Activating Token Index: 312

Text #8

Max Range: 0.3364. Min Range: -0.3364

Max Act: 0.2140. Min Act: -0.0000

Data Index: 774486 (C4 (Web Text))

Max Activating Token Index: 401

Text #9

Max Range: 0.3364. Min Range: -0.3364

Max Act: 0.2277. Min Act: -0.0000

Data Index: 225481 (C4 (Web Text))

Max Activating Token Index: 252

Text #10

Max Range: 0.3364. Min Range: -0.3364

Max Act: 0.2001. Min Act: -0.0000

Data Index: 518988 (C4 (Web Text))

Max Activating Token Index: 692

Text #11

Max Range: 0.3364. Min Range: -0.3364

Max Act: 0.2112. Min Act: -0.0000

Data Index: 772652 (C4 (Web Text))

Max Activating Token Index: 314

Text #12

Max Range: 0.3364. Min Range: -0.3364

Max Act: 0.2072. Min Act: -0.0000

Data Index: 317810 (C4 (Web Text))

Max Activating Token Index: 112

Text #13

Max Range: 0.3364. Min Range: -0.3364

Max Act: 0.2038. Min Act: -0.0000

Data Index: 1318452 (C4 (Web Text))

Max Activating Token Index: 213

Text #14

Max Range: 0.3364. Min Range: -0.3364

Max Act: 0.2097. Min Act: -0.0000

Data Index: 69615 (C4 (Web Text))

Max Activating Token Index: 336

Text #15

Max Range: 0.3364. Min Range: -0.3364

Max Act: 0.2078. Min Act: -0.0000

Data Index: 1338499 (C4 (Web Text))

Max Activating Token Index: 562

Text #16

Max Range: 0.3364. Min Range: -0.3364

Max Act: 0.1949. Min Act: -0.0000

Data Index: 1191646 (C4 (Web Text))

Max Activating Token Index: 217

Text #17

Max Range: 0.3364. Min Range: -0.3364

Max Act: 0.1932. Min Act: -0.0000

Data Index: 801582 (C4 (Web Text))

Max Activating Token Index: 225

Text #18

Max Range: 0.3364. Min Range: -0.3364

Max Act: 0.2042. Min Act: -0.0000

Data Index: 55099 (C4 (Web Text))

Max Activating Token Index: 145

Text #19

Max Range: 0.3364. Min Range: -0.3364

Max Act: 0.1935. Min Act: -0.0000

Data Index: 881303 (C4 (Web Text))

Max Activating Token Index: 504