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

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

Neuron 2886 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6862. Min Range: -2.6862

Max Act: 2.6862. Min Act: -0.0000

Data Index: 587737 (C4 (Web Text))

Max Activating Token Index: 838

Text #1

Max Range: 2.6862. Min Range: -2.6862

Max Act: 2.3388. Min Act: -0.0000

Data Index: 777535 (C4 (Web Text))

Max Activating Token Index: 975

Text #2

Max Range: 2.6862. Min Range: -2.6862

Max Act: 2.3322. Min Act: -0.0000

Data Index: 90835 (C4 (Web Text))

Max Activating Token Index: 930

Text #3

Max Range: 2.6862. Min Range: -2.6862

Max Act: 2.0927. Min Act: -0.0000

Data Index: 49964 (C4 (Web Text))

Max Activating Token Index: 639

Text #4

Max Range: 2.6862. Min Range: -2.6862

Max Act: 2.0228. Min Act: -0.0000

Data Index: 277076 (C4 (Web Text))

Max Activating Token Index: 214

Text #5

Max Range: 2.6862. Min Range: -2.6862

Max Act: 2.1480. Min Act: -0.0000

Data Index: 66541 (C4 (Web Text))

Max Activating Token Index: 36

Text #6

Max Range: 2.6862. Min Range: -2.6862

Max Act: 2.1522. Min Act: -0.0000

Data Index: 506934 (C4 (Web Text))

Max Activating Token Index: 219

Text #7

Max Range: 2.6862. Min Range: -2.6862

Max Act: 1.9090. Min Act: -0.0000

Data Index: 140475 (C4 (Web Text))

Max Activating Token Index: 184

Text #8

Max Range: 2.6862. Min Range: -2.6862

Max Act: 2.0710. Min Act: -0.0000

Data Index: 1322653 (C4 (Web Text))

Max Activating Token Index: 313

Text #9

Max Range: 2.6862. Min Range: -2.6862

Max Act: 1.9292. Min Act: -0.0000

Data Index: 1301270 (C4 (Web Text))

Max Activating Token Index: 493

Text #10

Max Range: 2.6862. Min Range: -2.6862

Max Act: 1.7276. Min Act: -0.0000

Data Index: 282544 (C4 (Web Text))

Max Activating Token Index: 788

Text #11

Max Range: 2.6862. Min Range: -2.6862

Max Act: 1.8898. Min Act: -0.0000

Data Index: 677170 (C4 (Web Text))

Max Activating Token Index: 114

Text #12

Max Range: 2.6862. Min Range: -2.6862

Max Act: 1.8040. Min Act: -0.0000

Data Index: 473079 (C4 (Web Text))

Max Activating Token Index: 906

Text #13

Max Range: 2.6862. Min Range: -2.6862

Max Act: 1.8949. Min Act: -0.0000

Data Index: 352372 (C4 (Web Text))

Max Activating Token Index: 732

Text #14

Max Range: 2.6862. Min Range: -2.6862

Max Act: 1.8011. Min Act: -0.0000

Data Index: 40847 (C4 (Web Text))

Max Activating Token Index: 573

Text #15

Max Range: 2.6862. Min Range: -2.6862

Max Act: 1.6894. Min Act: -0.0000

Data Index: 1019623 (C4 (Web Text))

Max Activating Token Index: 53

Text #16

Max Range: 2.6862. Min Range: -2.6862

Max Act: 1.6800. Min Act: -0.0000

Data Index: 465798 (C4 (Web Text))

Max Activating Token Index: 684

Text #17

Max Range: 2.6862. Min Range: -2.6862

Max Act: 1.7397. Min Act: -0.0000

Data Index: 1115907 (C4 (Web Text))

Max Activating Token Index: 596

Text #18

Max Range: 2.6862. Min Range: -2.6862

Max Act: 1.8076. Min Act: -0.0000

Data Index: 1243585 (C4 (Web Text))

Max Activating Token Index: 375

Text #19

Max Range: 2.6862. Min Range: -2.6862

Max Act: 1.6016. Min Act: -0.0000

Data Index: 1013426 (C4 (Web Text))

Max Activating Token Index: 422