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

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

Neuron 2091 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.9404. Min Range: -7.9404

Max Act: 7.9404. Min Act: -0.0000

Data Index: 120929 (C4 (Web Text))

Max Activating Token Index: 684

Text #1

Max Range: 7.9404. Min Range: -7.9404

Max Act: 6.9203. Min Act: -0.0000

Data Index: 355361 (C4 (Web Text))

Max Activating Token Index: 24

Text #2

Max Range: 7.9404. Min Range: -7.9404

Max Act: 6.8707. Min Act: -0.0000

Data Index: 1141827 (C4 (Web Text))

Max Activating Token Index: 541

Text #3

Max Range: 7.9404. Min Range: -7.9404

Max Act: 6.7852. Min Act: -0.0000

Data Index: 73585 (C4 (Web Text))

Max Activating Token Index: 563

Text #4

Max Range: 7.9404. Min Range: -7.9404

Max Act: 6.2488. Min Act: -0.0000

Data Index: 64346 (C4 (Web Text))

Max Activating Token Index: 668

Text #5

Max Range: 7.9404. Min Range: -7.9404

Max Act: 5.6534. Min Act: -0.0000

Data Index: 479889 (C4 (Web Text))

Max Activating Token Index: 716

Text #6

Max Range: 7.9404. Min Range: -7.9404

Max Act: 5.9814. Min Act: -0.0000

Data Index: 596483 (C4 (Web Text))

Max Activating Token Index: 420

Text #7

Max Range: 7.9404. Min Range: -7.9404

Max Act: 5.4228. Min Act: -0.0000

Data Index: 1083806 (C4 (Web Text))

Max Activating Token Index: 740

Text #8

Max Range: 7.9404. Min Range: -7.9404

Max Act: 5.4647. Min Act: -0.0000

Data Index: 105561 (C4 (Web Text))

Max Activating Token Index: 288

Text #9

Max Range: 7.9404. Min Range: -7.9404

Max Act: 5.1148. Min Act: -0.0000

Data Index: 1229716 (C4 (Web Text))

Max Activating Token Index: 447

Text #10

Max Range: 7.9404. Min Range: -7.9404

Max Act: 5.2163. Min Act: -0.0000

Data Index: 1069007 (C4 (Web Text))

Max Activating Token Index: 229

Text #11

Max Range: 7.9404. Min Range: -7.9404

Max Act: 5.1948. Min Act: -0.0000

Data Index: 1349034 (C4 (Web Text))

Max Activating Token Index: 602

Text #12

Max Range: 7.9404. Min Range: -7.9404

Max Act: 4.7425. Min Act: -0.0000

Data Index: 1120255 (C4 (Web Text))

Max Activating Token Index: 87

Text #13

Max Range: 7.9404. Min Range: -7.9404

Max Act: 5.2599. Min Act: -0.0000

Data Index: 672084 (C4 (Web Text))

Max Activating Token Index: 841

Text #14

Max Range: 7.9404. Min Range: -7.9404

Max Act: 4.8858. Min Act: -0.0000

Data Index: 161755 (C4 (Web Text))

Max Activating Token Index: 606

Text #15

Max Range: 7.9404. Min Range: -7.9404

Max Act: 4.8592. Min Act: -0.0000

Data Index: 452490 (C4 (Web Text))

Max Activating Token Index: 855

Text #16

Max Range: 7.9404. Min Range: -7.9404

Max Act: 4.5908. Min Act: -0.0000

Data Index: 760540 (C4 (Web Text))

Max Activating Token Index: 203

Text #17

Max Range: 7.9404. Min Range: -7.9404

Max Act: 4.5542. Min Act: -0.0000

Data Index: 1117540 (C4 (Web Text))

Max Activating Token Index: 204

Text #18

Max Range: 7.9404. Min Range: -7.9404

Max Act: 4.2882. Min Act: -0.0000

Data Index: 1140684 (C4 (Web Text))

Max Activating Token Index: 193

Text #19

Max Range: 7.9404. Min Range: -7.9404

Max Act: 4.2199. Min Act: -0.0000

Data Index: 1034850 (C4 (Web Text))

Max Activating Token Index: 454