Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 756 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0316. Min Act: -0.0002

Data Index: 634102 (C4 (Web Text))

Max Activating Token Index: 621

Text #1

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0328. Min Act: -0.0001

Data Index: 28414 (C4 (Web Text))

Max Activating Token Index: 331

Text #2

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0311. Min Act: -0.0002

Data Index: 484462 (C4 (Web Text))

Max Activating Token Index: 999

Text #3

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0303. Min Act: -0.0002

Data Index: 1087625 (C4 (Web Text))

Max Activating Token Index: 170

Text #4

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0307. Min Act: -0.0002

Data Index: 1326953 (C4 (Web Text))

Max Activating Token Index: 613

Text #5

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0287. Min Act: -0.0002

Data Index: 691654 (C4 (Web Text))

Max Activating Token Index: 1008

Text #6

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0300. Min Act: -0.0002

Data Index: 518788 (C4 (Web Text))

Max Activating Token Index: 246

Text #7

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0272. Min Act: -0.0002

Data Index: 672022 (C4 (Web Text))

Max Activating Token Index: 326

Text #8

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0287. Min Act: -0.0002

Data Index: 1038525 (C4 (Web Text))

Max Activating Token Index: 1014

Text #9

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0276. Min Act: -0.0002

Data Index: 1046347 (C4 (Web Text))

Max Activating Token Index: 1008

Text #10

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0279. Min Act: -0.0002

Data Index: 1347284 (C4 (Web Text))

Max Activating Token Index: 942

Text #11

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0280. Min Act: -0.0002

Data Index: 1426301 (Python Code)

Max Activating Token Index: 562

Text #12

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0289. Min Act: -0.0001

Data Index: 970961 (C4 (Web Text))

Max Activating Token Index: 884

Text #13

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0262. Min Act: -0.0002

Data Index: 435862 (C4 (Web Text))

Max Activating Token Index: 23

Text #14

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0268. Min Act: -0.0002

Data Index: 359872 (C4 (Web Text))

Max Activating Token Index: 975

Text #15

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0268. Min Act: -0.0002

Data Index: 1321720 (C4 (Web Text))

Max Activating Token Index: 641

Text #16

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0264. Min Act: -0.0002

Data Index: 13570 (C4 (Web Text))

Max Activating Token Index: 422

Text #17

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0268. Min Act: -0.0002

Data Index: 467342 (C4 (Web Text))

Max Activating Token Index: 405

Text #18

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0271. Min Act: -0.0002

Data Index: 558124 (C4 (Web Text))

Max Activating Token Index: 69

Text #19

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0264. Min Act: -0.0001

Data Index: 777412 (C4 (Web Text))

Max Activating Token Index: 813