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

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

Neuron 2230 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4239. Min Range: -0.4239

Max Act: 0.3800. Min Act: -0.0000

Data Index: 972480 (C4 (Web Text))

Max Activating Token Index: 888

Text #1

Max Range: 0.4239. Min Range: -0.4239

Max Act: 0.4239. Min Act: -0.0000

Data Index: 844109 (C4 (Web Text))

Max Activating Token Index: 361

Text #2

Max Range: 0.4239. Min Range: -0.4239

Max Act: 0.3745. Min Act: -0.0000

Data Index: 1353837 (C4 (Web Text))

Max Activating Token Index: 364

Text #3

Max Range: 0.4239. Min Range: -0.4239

Max Act: 0.3976. Min Act: -0.0000

Data Index: 953848 (C4 (Web Text))

Max Activating Token Index: 133

Text #4

Max Range: 0.4239. Min Range: -0.4239

Max Act: 0.4068. Min Act: -0.0000

Data Index: 744400 (C4 (Web Text))

Max Activating Token Index: 628

Text #5

Max Range: 0.4239. Min Range: -0.4239

Max Act: 0.3455. Min Act: -0.0000

Data Index: 1217087 (C4 (Web Text))

Max Activating Token Index: 976

Text #6

Max Range: 0.4239. Min Range: -0.4239

Max Act: 0.3752. Min Act: -0.0000

Data Index: 836870 (C4 (Web Text))

Max Activating Token Index: 943

Text #7

Max Range: 0.4239. Min Range: -0.4239

Max Act: 0.3358. Min Act: -0.0000

Data Index: 1305462 (C4 (Web Text))

Max Activating Token Index: 213

Text #8

Max Range: 0.4239. Min Range: -0.4239

Max Act: 0.3578. Min Act: -0.0000

Data Index: 1282765 (C4 (Web Text))

Max Activating Token Index: 986

Text #9

Max Range: 0.4239. Min Range: -0.4239

Max Act: 0.3275. Min Act: -0.0000

Data Index: 69729 (C4 (Web Text))

Max Activating Token Index: 669

Text #10

Max Range: 0.4239. Min Range: -0.4239

Max Act: 0.3316. Min Act: -0.0000

Data Index: 391814 (C4 (Web Text))

Max Activating Token Index: 751

Text #11

Max Range: 0.4239. Min Range: -0.4239

Max Act: 0.3410. Min Act: -0.0000

Data Index: 736232 (C4 (Web Text))

Max Activating Token Index: 340

Text #12

Max Range: 0.4239. Min Range: -0.4239

Max Act: 0.3365. Min Act: -0.0000

Data Index: 1098073 (C4 (Web Text))

Max Activating Token Index: 442

Text #13

Max Range: 0.4239. Min Range: -0.4239

Max Act: 0.3233. Min Act: -0.0000

Data Index: 821773 (C4 (Web Text))

Max Activating Token Index: 149

Text #14

Max Range: 0.4239. Min Range: -0.4239

Max Act: 0.3129. Min Act: -0.0000

Data Index: 328204 (C4 (Web Text))

Max Activating Token Index: 869

Text #15

Max Range: 0.4239. Min Range: -0.4239

Max Act: 0.3428. Min Act: -0.0000

Data Index: 1054368 (C4 (Web Text))

Max Activating Token Index: 294

Text #16

Max Range: 0.4239. Min Range: -0.4239

Max Act: 0.3073. Min Act: -0.0000

Data Index: 1286906 (C4 (Web Text))

Max Activating Token Index: 608

Text #17

Max Range: 0.4239. Min Range: -0.4239

Max Act: 0.3140. Min Act: -0.0000

Data Index: 65064 (C4 (Web Text))

Max Activating Token Index: 334

Text #18

Max Range: 0.4239. Min Range: -0.4239

Max Act: 0.3153. Min Act: -0.0000

Data Index: 158677 (C4 (Web Text))

Max Activating Token Index: 124

Text #19

Max Range: 0.4239. Min Range: -0.4239

Max Act: 0.2948. Min Act: -0.0000

Data Index: 38443 (C4 (Web Text))

Max Activating Token Index: 896