Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3151 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.9031. Min Range: -0.9031

Max Act: 0.8780. Min Act: -0.0000

Data Index: 15156 (C4 (Web Text))

Max Activating Token Index: 665

Text #1

Max Range: 0.9031. Min Range: -0.9031

Max Act: 0.9031. Min Act: -0.0000

Data Index: 1066071 (C4 (Web Text))

Max Activating Token Index: 628

Text #2

Max Range: 0.9031. Min Range: -0.9031

Max Act: 0.8383. Min Act: -0.0000

Data Index: 975828 (C4 (Web Text))

Max Activating Token Index: 487

Text #3

Max Range: 0.9031. Min Range: -0.9031

Max Act: 0.8014. Min Act: -0.0000

Data Index: 1104259 (C4 (Web Text))

Max Activating Token Index: 947

Text #4

Max Range: 0.9031. Min Range: -0.9031

Max Act: 0.7332. Min Act: -0.0000

Data Index: 1272547 (C4 (Web Text))

Max Activating Token Index: 669

Text #5

Max Range: 0.9031. Min Range: -0.9031

Max Act: 0.6443. Min Act: -0.0000

Data Index: 245596 (C4 (Web Text))

Max Activating Token Index: 730

Text #6

Max Range: 0.9031. Min Range: -0.9031

Max Act: 0.6419. Min Act: -0.0000

Data Index: 443421 (C4 (Web Text))

Max Activating Token Index: 1011

Text #7

Max Range: 0.9031. Min Range: -0.9031

Max Act: 0.6903. Min Act: -0.0000

Data Index: 876972 (C4 (Web Text))

Max Activating Token Index: 929

Text #8

Max Range: 0.9031. Min Range: -0.9031

Max Act: 0.7003. Min Act: -0.0000

Data Index: 1190479 (C4 (Web Text))

Max Activating Token Index: 83

Text #9

Max Range: 0.9031. Min Range: -0.9031

Max Act: 0.6294. Min Act: -0.0000

Data Index: 88517 (C4 (Web Text))

Max Activating Token Index: 121

Text #10

Max Range: 0.9031. Min Range: -0.9031

Max Act: 0.6358. Min Act: -0.0000

Data Index: 158794 (C4 (Web Text))

Max Activating Token Index: 820

Text #11

Max Range: 0.9031. Min Range: -0.9031

Max Act: 0.6523. Min Act: -0.0000

Data Index: 283248 (C4 (Web Text))

Max Activating Token Index: 690

Text #12

Max Range: 0.9031. Min Range: -0.9031

Max Act: 0.6479. Min Act: -0.0000

Data Index: 295491 (C4 (Web Text))

Max Activating Token Index: 361

Text #13

Max Range: 0.9031. Min Range: -0.9031

Max Act: 0.5984. Min Act: -0.0000

Data Index: 537367 (C4 (Web Text))

Max Activating Token Index: 353

Text #14

Max Range: 0.9031. Min Range: -0.9031

Max Act: 0.6207. Min Act: -0.0000

Data Index: 426678 (C4 (Web Text))

Max Activating Token Index: 471

Text #15

Max Range: 0.9031. Min Range: -0.9031

Max Act: 0.6018. Min Act: -0.0000

Data Index: 138861 (C4 (Web Text))

Max Activating Token Index: 913

Text #16

Max Range: 0.9031. Min Range: -0.9031

Max Act: 0.5715. Min Act: -0.0000

Data Index: 795005 (C4 (Web Text))

Max Activating Token Index: 122

Text #17

Max Range: 0.9031. Min Range: -0.9031

Max Act: 0.5932. Min Act: -0.0000

Data Index: 715298 (C4 (Web Text))

Max Activating Token Index: 746

Text #18

Max Range: 0.9031. Min Range: -0.9031

Max Act: 0.6075. Min Act: -0.0000

Data Index: 781151 (C4 (Web Text))

Max Activating Token Index: 722

Text #19

Max Range: 0.9031. Min Range: -0.9031

Max Act: 0.5859. Min Act: -0.0000

Data Index: 1188875 (C4 (Web Text))

Max Activating Token Index: 322