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

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

Neuron 5924 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.3623. Min Range: -4.3623

Max Act: 4.3623. Min Act: -0.0000

Data Index: 434334 (C4 (Web Text))

Max Activating Token Index: 932

Text #1

Max Range: 4.3623. Min Range: -4.3623

Max Act: 4.1586. Min Act: -0.0000

Data Index: 481154 (C4 (Web Text))

Max Activating Token Index: 338

Text #2

Max Range: 4.3623. Min Range: -4.3623

Max Act: 4.2184. Min Act: -0.0000

Data Index: 986976 (C4 (Web Text))

Max Activating Token Index: 40

Text #3

Max Range: 4.3623. Min Range: -4.3623

Max Act: 3.9411. Min Act: -0.0000

Data Index: 138573 (C4 (Web Text))

Max Activating Token Index: 49

Text #4

Max Range: 4.3623. Min Range: -4.3623

Max Act: 3.7050. Min Act: -0.0000

Data Index: 1290549 (C4 (Web Text))

Max Activating Token Index: 996

Text #5

Max Range: 4.3623. Min Range: -4.3623

Max Act: 3.7289. Min Act: -0.0000

Data Index: 1313335 (C4 (Web Text))

Max Activating Token Index: 215

Text #6

Max Range: 4.3623. Min Range: -4.3623

Max Act: 3.5671. Min Act: -0.0000

Data Index: 607697 (C4 (Web Text))

Max Activating Token Index: 333

Text #7

Max Range: 4.3623. Min Range: -4.3623

Max Act: 3.6427. Min Act: -0.0000

Data Index: 949076 (C4 (Web Text))

Max Activating Token Index: 174

Text #8

Max Range: 4.3623. Min Range: -4.3623

Max Act: 3.4357. Min Act: -0.0000

Data Index: 220848 (C4 (Web Text))

Max Activating Token Index: 102

Text #9

Max Range: 4.3623. Min Range: -4.3623

Max Act: 3.5177. Min Act: -0.0000

Data Index: 823243 (C4 (Web Text))

Max Activating Token Index: 200

Text #10

Max Range: 4.3623. Min Range: -4.3623

Max Act: 3.4711. Min Act: -0.0000

Data Index: 1274779 (C4 (Web Text))

Max Activating Token Index: 228

Text #11

Max Range: 4.3623. Min Range: -4.3623

Max Act: 3.5521. Min Act: -0.0000

Data Index: 696693 (C4 (Web Text))

Max Activating Token Index: 714

Text #12

Max Range: 4.3623. Min Range: -4.3623

Max Act: 3.3879. Min Act: -0.0000

Data Index: 645058 (C4 (Web Text))

Max Activating Token Index: 825

Text #13

Max Range: 4.3623. Min Range: -4.3623

Max Act: 3.3385. Min Act: -0.0000

Data Index: 20413 (C4 (Web Text))

Max Activating Token Index: 986

Text #14

Max Range: 4.3623. Min Range: -4.3623

Max Act: 3.4582. Min Act: -0.0000

Data Index: 566998 (C4 (Web Text))

Max Activating Token Index: 154

Text #15

Max Range: 4.3623. Min Range: -4.3623

Max Act: 3.4342. Min Act: -0.0000

Data Index: 1280394 (C4 (Web Text))

Max Activating Token Index: 958

Text #16

Max Range: 4.3623. Min Range: -4.3623

Max Act: 3.0048. Min Act: -0.0000

Data Index: 1079317 (C4 (Web Text))

Max Activating Token Index: 727

Text #17

Max Range: 4.3623. Min Range: -4.3623

Max Act: 3.2421. Min Act: -0.0000

Data Index: 104225 (C4 (Web Text))

Max Activating Token Index: 793

Text #18

Max Range: 4.3623. Min Range: -4.3623

Max Act: 3.2453. Min Act: -0.0000

Data Index: 1061363 (C4 (Web Text))

Max Activating Token Index: 228

Text #19

Max Range: 4.3623. Min Range: -4.3623

Max Act: 3.2630. Min Act: -0.0000

Data Index: 1124768 (C4 (Web Text))

Max Activating Token Index: 1021