Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 2019 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0620. Min Act: -0.0002

Data Index: 741770 (C4 (Web Text))

Max Activating Token Index: 960

Text #1

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0422. Min Act: -0.0003

Data Index: 708339 (C4 (Web Text))

Max Activating Token Index: 245

Text #2

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0395. Min Act: -0.0003

Data Index: 689514 (C4 (Web Text))

Max Activating Token Index: 767

Text #3

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0358. Min Act: -0.0003

Data Index: 433399 (C4 (Web Text))

Max Activating Token Index: 281

Text #4

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0336. Min Act: -0.0003

Data Index: 1561234 (Python Code)

Max Activating Token Index: 688

Text #5

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0327. Min Act: -0.0003

Data Index: 1493773 (Python Code)

Max Activating Token Index: 998

Text #6

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0320. Min Act: -0.0003

Data Index: 1365497 (Python Code)

Max Activating Token Index: 490

Text #7

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0322. Min Act: -0.0003

Data Index: 1541886 (Python Code)

Max Activating Token Index: 520

Text #8

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0312. Min Act: -0.0003

Data Index: 1373874 (Python Code)

Max Activating Token Index: 617

Text #9

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0302. Min Act: -0.0003

Data Index: 797879 (C4 (Web Text))

Max Activating Token Index: 381

Text #10

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0317. Min Act: -0.0002

Data Index: 1596070 (Python Code)

Max Activating Token Index: 186

Text #11

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0293. Min Act: -0.0003

Data Index: 201447 (C4 (Web Text))

Max Activating Token Index: 741

Text #12

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0309. Min Act: -0.0003

Data Index: 894747 (C4 (Web Text))

Max Activating Token Index: 411

Text #13

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0378. Min Act: -0.0003

Data Index: 1114249 (C4 (Web Text))

Max Activating Token Index: 703

Text #14

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0302. Min Act: -0.0003

Data Index: 1406209 (Python Code)

Max Activating Token Index: 937

Text #15

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0310. Min Act: -0.0002

Data Index: 1601810 (Python Code)

Max Activating Token Index: 570

Text #16

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0303. Min Act: -0.0002

Data Index: 1400989 (Python Code)

Max Activating Token Index: 780

Text #17

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0291. Min Act: -0.0003

Data Index: 1427364 (Python Code)

Max Activating Token Index: 890

Text #18

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0303. Min Act: -0.0002

Data Index: 1589969 (Python Code)

Max Activating Token Index: 938

Text #19

Max Range: 0.0620. Min Range: -0.0620

Max Act: 0.0292. Min Act: -0.0003

Data Index: 1418803 (Python Code)

Max Activating Token Index: 606