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

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

Neuron 5745 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: 0.3668. Min Range: -0.3668

Max Act: 0.3668. Min Act: -0.0000

Data Index: 138871 (C4 (Web Text))

Max Activating Token Index: 854

Text #1

Max Range: 0.3668. Min Range: -0.3668

Max Act: 0.1749. Min Act: -0.0000

Data Index: 584093 (C4 (Web Text))

Max Activating Token Index: 398

Text #2

Max Range: 0.3668. Min Range: -0.3668

Max Act: 0.2111. Min Act: -0.0000

Data Index: 993392 (C4 (Web Text))

Max Activating Token Index: 18

Text #3

Max Range: 0.3668. Min Range: -0.3668

Max Act: 0.2158. Min Act: -0.0000

Data Index: 1033585 (C4 (Web Text))

Max Activating Token Index: 405

Text #4

Max Range: 0.3668. Min Range: -0.3668

Max Act: 0.2217. Min Act: -0.0000

Data Index: 263538 (C4 (Web Text))

Max Activating Token Index: 676

Text #5

Max Range: 0.3668. Min Range: -0.3668

Max Act: 0.1836. Min Act: -0.0000

Data Index: 323873 (C4 (Web Text))

Max Activating Token Index: 803

Text #6

Max Range: 0.3668. Min Range: -0.3668

Max Act: 0.1947. Min Act: -0.0000

Data Index: 832352 (C4 (Web Text))

Max Activating Token Index: 985

Text #7

Max Range: 0.3668. Min Range: -0.3668

Max Act: 0.1615. Min Act: -0.0000

Data Index: 548564 (C4 (Web Text))

Max Activating Token Index: 1003

Text #8

Max Range: 0.3668. Min Range: -0.3668

Max Act: 0.1604. Min Act: -0.0000

Data Index: 526921 (C4 (Web Text))

Max Activating Token Index: 861

Text #9

Max Range: 0.3668. Min Range: -0.3668

Max Act: 0.1633. Min Act: -0.0000

Data Index: 664624 (C4 (Web Text))

Max Activating Token Index: 93

Text #10

Max Range: 0.3668. Min Range: -0.3668

Max Act: 0.1801. Min Act: -0.0000

Data Index: 295849 (C4 (Web Text))

Max Activating Token Index: 818

Text #11

Max Range: 0.3668. Min Range: -0.3668

Max Act: 0.1641. Min Act: -0.0000

Data Index: 330757 (C4 (Web Text))

Max Activating Token Index: 556

Text #12

Max Range: 0.3668. Min Range: -0.3668

Max Act: 0.1709. Min Act: -0.0000

Data Index: 868293 (C4 (Web Text))

Max Activating Token Index: 594

Text #13

Max Range: 0.3668. Min Range: -0.3668

Max Act: 0.1606. Min Act: -0.0000

Data Index: 894980 (C4 (Web Text))

Max Activating Token Index: 519

Text #14

Max Range: 0.3668. Min Range: -0.3668

Max Act: 0.1373. Min Act: -0.0000

Data Index: 1009220 (C4 (Web Text))

Max Activating Token Index: 201

Text #15

Max Range: 0.3668. Min Range: -0.3668

Max Act: 0.1605. Min Act: -0.0000

Data Index: 489133 (C4 (Web Text))

Max Activating Token Index: 566

Text #16

Max Range: 0.3668. Min Range: -0.3668

Max Act: 0.1225. Min Act: -0.0000

Data Index: 342171 (C4 (Web Text))

Max Activating Token Index: 472

Text #17

Max Range: 0.3668. Min Range: -0.3668

Max Act: 0.1408. Min Act: -0.0000

Data Index: 363215 (C4 (Web Text))

Max Activating Token Index: 946

Text #18

Max Range: 0.3668. Min Range: -0.3668

Max Act: 0.1447. Min Act: -0.0000

Data Index: 1154854 (C4 (Web Text))

Max Activating Token Index: 113

Text #19

Max Range: 0.3668. Min Range: -0.3668

Max Act: 0.1478. Min Act: -0.0000

Data Index: 1174196 (C4 (Web Text))

Max Activating Token Index: 267