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

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

Neuron 5624 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: 6.5211. Min Range: -6.5211

Max Act: 6.5211. Min Act: 0.0000

Data Index: 46764 (C4 (Web Text))

Max Activating Token Index: 221

Text #1

Max Range: 6.5211. Min Range: -6.5211

Max Act: 4.2401. Min Act: -0.0000

Data Index: 588424 (C4 (Web Text))

Max Activating Token Index: 484

Text #2

Max Range: 6.5211. Min Range: -6.5211

Max Act: 4.7240. Min Act: -0.0000

Data Index: 958308 (C4 (Web Text))

Max Activating Token Index: 81

Text #3

Max Range: 6.5211. Min Range: -6.5211

Max Act: 4.6316. Min Act: -0.0000

Data Index: 260483 (C4 (Web Text))

Max Activating Token Index: 114

Text #4

Max Range: 6.5211. Min Range: -6.5211

Max Act: 3.4843. Min Act: -0.0000

Data Index: 128237 (C4 (Web Text))

Max Activating Token Index: 65

Text #5

Max Range: 6.5211. Min Range: -6.5211

Max Act: 3.8386. Min Act: -0.0000

Data Index: 973251 (C4 (Web Text))

Max Activating Token Index: 109

Text #6

Max Range: 6.5211. Min Range: -6.5211

Max Act: 4.5960. Min Act: -0.0000

Data Index: 1263321 (C4 (Web Text))

Max Activating Token Index: 863

Text #7

Max Range: 6.5211. Min Range: -6.5211

Max Act: 3.2315. Min Act: -0.0000

Data Index: 787044 (C4 (Web Text))

Max Activating Token Index: 519

Text #8

Max Range: 6.5211. Min Range: -6.5211

Max Act: 4.1467. Min Act: -0.0000

Data Index: 167967 (C4 (Web Text))

Max Activating Token Index: 86

Text #9

Max Range: 6.5211. Min Range: -6.5211

Max Act: 4.0579. Min Act: 0.0000

Data Index: 164116 (C4 (Web Text))

Max Activating Token Index: 402

Text #10

Max Range: 6.5211. Min Range: -6.5211

Max Act: 4.1099. Min Act: -0.0000

Data Index: 839853 (C4 (Web Text))

Max Activating Token Index: 631

Text #11

Max Range: 6.5211. Min Range: -6.5211

Max Act: 2.6359. Min Act: -0.0000

Data Index: 1248874 (C4 (Web Text))

Max Activating Token Index: 1014

Text #12

Max Range: 6.5211. Min Range: -6.5211

Max Act: 3.3799. Min Act: -0.0000

Data Index: 322077 (C4 (Web Text))

Max Activating Token Index: 924

Text #13

Max Range: 6.5211. Min Range: -6.5211

Max Act: 3.4891. Min Act: -0.0000

Data Index: 1216862 (C4 (Web Text))

Max Activating Token Index: 673

Text #14

Max Range: 6.5211. Min Range: -6.5211

Max Act: 2.7324. Min Act: -0.0000

Data Index: 1286497 (C4 (Web Text))

Max Activating Token Index: 34

Text #15

Max Range: 6.5211. Min Range: -6.5211

Max Act: 2.8607. Min Act: -0.0000

Data Index: 1164137 (C4 (Web Text))

Max Activating Token Index: 176

Text #16

Max Range: 6.5211. Min Range: -6.5211

Max Act: 3.6688. Min Act: -0.0000

Data Index: 1154270 (C4 (Web Text))

Max Activating Token Index: 688

Text #17

Max Range: 6.5211. Min Range: -6.5211

Max Act: 2.8383. Min Act: -0.0000

Data Index: 1233729 (C4 (Web Text))

Max Activating Token Index: 368

Text #18

Max Range: 6.5211. Min Range: -6.5211

Max Act: 2.8955. Min Act: -0.0000

Data Index: 810486 (C4 (Web Text))

Max Activating Token Index: 985

Text #19

Max Range: 6.5211. Min Range: -6.5211

Max Act: 1.7888. Min Act: -0.0000

Data Index: 31035 (C4 (Web Text))

Max Activating Token Index: 867