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

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

Neuron 3385 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9183. Min Range: -1.9183

Max Act: 1.9183. Min Act: -0.0000

Data Index: 73278 (C4 (Web Text))

Max Activating Token Index: 56

Text #1

Max Range: 1.9183. Min Range: -1.9183

Max Act: 1.7269. Min Act: -0.0000

Data Index: 857807 (C4 (Web Text))

Max Activating Token Index: 270

Text #2

Max Range: 1.9183. Min Range: -1.9183

Max Act: 1.4543. Min Act: -0.0000

Data Index: 59403 (C4 (Web Text))

Max Activating Token Index: 409

Text #3

Max Range: 1.9183. Min Range: -1.9183

Max Act: 1.5759. Min Act: -0.0000

Data Index: 244779 (C4 (Web Text))

Max Activating Token Index: 802

Text #4

Max Range: 1.9183. Min Range: -1.9183

Max Act: 1.3956. Min Act: -0.0000

Data Index: 600189 (C4 (Web Text))

Max Activating Token Index: 405

Text #5

Max Range: 1.9183. Min Range: -1.9183

Max Act: 1.3797. Min Act: -0.0000

Data Index: 877521 (C4 (Web Text))

Max Activating Token Index: 865

Text #6

Max Range: 1.9183. Min Range: -1.9183

Max Act: 1.4353. Min Act: -0.0000

Data Index: 14506 (C4 (Web Text))

Max Activating Token Index: 927

Text #7

Max Range: 1.9183. Min Range: -1.9183

Max Act: 1.4226. Min Act: -0.0000

Data Index: 783150 (C4 (Web Text))

Max Activating Token Index: 134

Text #8

Max Range: 1.9183. Min Range: -1.9183

Max Act: 1.4219. Min Act: -0.0000

Data Index: 727815 (C4 (Web Text))

Max Activating Token Index: 936

Text #9

Max Range: 1.9183. Min Range: -1.9183

Max Act: 1.3996. Min Act: -0.0000

Data Index: 1070318 (C4 (Web Text))

Max Activating Token Index: 957

Text #10

Max Range: 1.9183. Min Range: -1.9183

Max Act: 1.4035. Min Act: -0.0000

Data Index: 142577 (C4 (Web Text))

Max Activating Token Index: 194

Text #11

Max Range: 1.9183. Min Range: -1.9183

Max Act: 1.3870. Min Act: -0.0000

Data Index: 803968 (C4 (Web Text))

Max Activating Token Index: 966

Text #12

Max Range: 1.9183. Min Range: -1.9183

Max Act: 1.3001. Min Act: -0.0000

Data Index: 934477 (C4 (Web Text))

Max Activating Token Index: 540

Text #13

Max Range: 1.9183. Min Range: -1.9183

Max Act: 1.2732. Min Act: -0.0000

Data Index: 687721 (C4 (Web Text))

Max Activating Token Index: 1005

Text #14

Max Range: 1.9183. Min Range: -1.9183

Max Act: 1.3536. Min Act: -0.0000

Data Index: 151487 (C4 (Web Text))

Max Activating Token Index: 424

Text #15

Max Range: 1.9183. Min Range: -1.9183

Max Act: 1.3586. Min Act: -0.0000

Data Index: 606140 (C4 (Web Text))

Max Activating Token Index: 486

Text #16

Max Range: 1.9183. Min Range: -1.9183

Max Act: 1.3555. Min Act: -0.0000

Data Index: 864576 (C4 (Web Text))

Max Activating Token Index: 794

Text #17

Max Range: 1.9183. Min Range: -1.9183

Max Act: 1.0795. Min Act: -0.0000

Data Index: 457023 (C4 (Web Text))

Max Activating Token Index: 836

Text #18

Max Range: 1.9183. Min Range: -1.9183

Max Act: 1.4170. Min Act: -0.0000

Data Index: 980016 (C4 (Web Text))

Max Activating Token Index: 461

Text #19

Max Range: 1.9183. Min Range: -1.9183

Max Act: 1.2048. Min Act: -0.0000

Data Index: 1090575 (C4 (Web Text))

Max Activating Token Index: 893