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

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

Neuron 652 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3989. Min Range: -1.3989

Max Act: 1.3914. Min Act: -0.0000

Data Index: 886314 (C4 (Web Text))

Max Activating Token Index: 153

Text #1

Max Range: 1.3989. Min Range: -1.3989

Max Act: 1.3989. Min Act: -0.0000

Data Index: 985613 (C4 (Web Text))

Max Activating Token Index: 158

Text #2

Max Range: 1.3989. Min Range: -1.3989

Max Act: 1.3069. Min Act: -0.0000

Data Index: 425971 (C4 (Web Text))

Max Activating Token Index: 91

Text #3

Max Range: 1.3989. Min Range: -1.3989

Max Act: 1.2235. Min Act: -0.0000

Data Index: 719404 (C4 (Web Text))

Max Activating Token Index: 583

Text #4

Max Range: 1.3989. Min Range: -1.3989

Max Act: 1.1014. Min Act: -0.0000

Data Index: 800335 (C4 (Web Text))

Max Activating Token Index: 327

Text #5

Max Range: 1.3989. Min Range: -1.3989

Max Act: 1.1847. Min Act: -0.0000

Data Index: 627468 (C4 (Web Text))

Max Activating Token Index: 155

Text #6

Max Range: 1.3989. Min Range: -1.3989

Max Act: 1.0995. Min Act: -0.0000

Data Index: 740584 (C4 (Web Text))

Max Activating Token Index: 331

Text #7

Max Range: 1.3989. Min Range: -1.3989

Max Act: 1.1787. Min Act: -0.0000

Data Index: 1041334 (C4 (Web Text))

Max Activating Token Index: 212

Text #8

Max Range: 1.3989. Min Range: -1.3989

Max Act: 1.1802. Min Act: -0.0000

Data Index: 1200460 (C4 (Web Text))

Max Activating Token Index: 88

Text #9

Max Range: 1.3989. Min Range: -1.3989

Max Act: 1.1422. Min Act: -0.0000

Data Index: 1031816 (C4 (Web Text))

Max Activating Token Index: 407

Text #10

Max Range: 1.3989. Min Range: -1.3989

Max Act: 1.1839. Min Act: -0.0000

Data Index: 1093487 (C4 (Web Text))

Max Activating Token Index: 205

Text #11

Max Range: 1.3989. Min Range: -1.3989

Max Act: 1.0214. Min Act: -0.0000

Data Index: 112365 (C4 (Web Text))

Max Activating Token Index: 585

Text #12

Max Range: 1.3989. Min Range: -1.3989

Max Act: 1.0888. Min Act: -0.0000

Data Index: 295296 (C4 (Web Text))

Max Activating Token Index: 814

Text #13

Max Range: 1.3989. Min Range: -1.3989

Max Act: 1.0130. Min Act: -0.0000

Data Index: 108260 (C4 (Web Text))

Max Activating Token Index: 494

Text #14

Max Range: 1.3989. Min Range: -1.3989

Max Act: 0.8863. Min Act: -0.0000

Data Index: 1331114 (C4 (Web Text))

Max Activating Token Index: 632

Text #15

Max Range: 1.3989. Min Range: -1.3989

Max Act: 1.0393. Min Act: -0.0000

Data Index: 837458 (C4 (Web Text))

Max Activating Token Index: 858

Text #16

Max Range: 1.3989. Min Range: -1.3989

Max Act: 1.0210. Min Act: -0.0000

Data Index: 392404 (C4 (Web Text))

Max Activating Token Index: 166

Text #17

Max Range: 1.3989. Min Range: -1.3989

Max Act: 0.9423. Min Act: -0.0001

Data Index: 1027791 (C4 (Web Text))

Max Activating Token Index: 179

Text #18

Max Range: 1.3989. Min Range: -1.3989

Max Act: 0.9204. Min Act: -0.0000

Data Index: 1276295 (C4 (Web Text))

Max Activating Token Index: 36

Text #19

Max Range: 1.3989. Min Range: -1.3989

Max Act: 0.8221. Min Act: -0.0000

Data Index: 688543 (C4 (Web Text))

Max Activating Token Index: 893