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

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

Neuron 4557 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3603. Min Range: -1.3603

Max Act: 1.3376. Min Act: -0.0000

Data Index: 28382 (C4 (Web Text))

Max Activating Token Index: 404

Text #1

Max Range: 1.3603. Min Range: -1.3603

Max Act: 1.2980. Min Act: -0.0000

Data Index: 478135 (C4 (Web Text))

Max Activating Token Index: 606

Text #2

Max Range: 1.3603. Min Range: -1.3603

Max Act: 1.3603. Min Act: -0.0000

Data Index: 3692 (C4 (Web Text))

Max Activating Token Index: 824

Text #3

Max Range: 1.3603. Min Range: -1.3603

Max Act: 1.2180. Min Act: -0.0000

Data Index: 181780 (C4 (Web Text))

Max Activating Token Index: 524

Text #4

Max Range: 1.3603. Min Range: -1.3603

Max Act: 1.3041. Min Act: -0.0000

Data Index: 74852 (C4 (Web Text))

Max Activating Token Index: 1006

Text #5

Max Range: 1.3603. Min Range: -1.3603

Max Act: 1.2398. Min Act: -0.0000

Data Index: 1352043 (C4 (Web Text))

Max Activating Token Index: 1006

Text #6

Max Range: 1.3603. Min Range: -1.3603

Max Act: 1.2677. Min Act: -0.0000

Data Index: 15662 (C4 (Web Text))

Max Activating Token Index: 644

Text #7

Max Range: 1.3603. Min Range: -1.3603

Max Act: 1.1485. Min Act: -0.0000

Data Index: 693540 (C4 (Web Text))

Max Activating Token Index: 806

Text #8

Max Range: 1.3603. Min Range: -1.3603

Max Act: 1.0296. Min Act: -0.0000

Data Index: 590862 (C4 (Web Text))

Max Activating Token Index: 315

Text #9

Max Range: 1.3603. Min Range: -1.3603

Max Act: 0.9799. Min Act: -0.0000

Data Index: 1067042 (C4 (Web Text))

Max Activating Token Index: 119

Text #10

Max Range: 1.3603. Min Range: -1.3603

Max Act: 1.0895. Min Act: -0.0000

Data Index: 1083979 (C4 (Web Text))

Max Activating Token Index: 920

Text #11

Max Range: 1.3603. Min Range: -1.3603

Max Act: 1.1282. Min Act: -0.0000

Data Index: 1341192 (C4 (Web Text))

Max Activating Token Index: 120

Text #12

Max Range: 1.3603. Min Range: -1.3603

Max Act: 0.9480. Min Act: -0.0000

Data Index: 1124071 (C4 (Web Text))

Max Activating Token Index: 212

Text #13

Max Range: 1.3603. Min Range: -1.3603

Max Act: 0.9372. Min Act: -0.0000

Data Index: 128683 (C4 (Web Text))

Max Activating Token Index: 893

Text #14

Max Range: 1.3603. Min Range: -1.3603

Max Act: 0.8928. Min Act: -0.0000

Data Index: 152905 (C4 (Web Text))

Max Activating Token Index: 303

Text #15

Max Range: 1.3603. Min Range: -1.3603

Max Act: 0.9645. Min Act: -0.0000

Data Index: 860870 (C4 (Web Text))

Max Activating Token Index: 973

Text #16

Max Range: 1.3603. Min Range: -1.3603

Max Act: 0.9268. Min Act: -0.0000

Data Index: 746493 (C4 (Web Text))

Max Activating Token Index: 634

Text #17

Max Range: 1.3603. Min Range: -1.3603

Max Act: 0.8978. Min Act: -0.0000

Data Index: 488734 (C4 (Web Text))

Max Activating Token Index: 380

Text #18

Max Range: 1.3603. Min Range: -1.3603

Max Act: 0.9236. Min Act: -0.0000

Data Index: 209366 (C4 (Web Text))

Max Activating Token Index: 108

Text #19

Max Range: 1.3603. Min Range: -1.3603

Max Act: 0.8159. Min Act: -0.0000

Data Index: 1163142 (C4 (Web Text))

Max Activating Token Index: 216