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

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

Neuron 729 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0380. Min Act: -0.0002

Data Index: 1287036 (C4 (Web Text))

Max Activating Token Index: 994

Text #1

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0331. Min Act: -0.0002

Data Index: 795508 (C4 (Web Text))

Max Activating Token Index: 91

Text #2

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0325. Min Act: -0.0002

Data Index: 504359 (C4 (Web Text))

Max Activating Token Index: 286

Text #3

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0283. Min Act: -0.0002

Data Index: 1263408 (C4 (Web Text))

Max Activating Token Index: 807

Text #4

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0307. Min Act: -0.0002

Data Index: 419850 (C4 (Web Text))

Max Activating Token Index: 817

Text #5

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0317. Min Act: -0.0002

Data Index: 1335301 (C4 (Web Text))

Max Activating Token Index: 208

Text #6

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0297. Min Act: -0.0002

Data Index: 113253 (C4 (Web Text))

Max Activating Token Index: 341

Text #7

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0329. Min Act: -0.0002

Data Index: 1242252 (C4 (Web Text))

Max Activating Token Index: 641

Text #8

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0297. Min Act: -0.0002

Data Index: 368081 (C4 (Web Text))

Max Activating Token Index: 745

Text #9

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0303. Min Act: -0.0003

Data Index: 1048440 (C4 (Web Text))

Max Activating Token Index: 339

Text #10

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0292. Min Act: -0.0002

Data Index: 726967 (C4 (Web Text))

Max Activating Token Index: 645

Text #11

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0263. Min Act: -0.0002

Data Index: 610109 (C4 (Web Text))

Max Activating Token Index: 214

Text #12

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0285. Min Act: -0.0002

Data Index: 431250 (C4 (Web Text))

Max Activating Token Index: 901

Text #13

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0244. Min Act: -0.0002

Data Index: 1014384 (C4 (Web Text))

Max Activating Token Index: 210

Text #14

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0296. Min Act: -0.0002

Data Index: 1083156 (C4 (Web Text))

Max Activating Token Index: 904

Text #15

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0292. Min Act: -0.0002

Data Index: 1339016 (C4 (Web Text))

Max Activating Token Index: 318

Text #16

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0276. Min Act: -0.0002

Data Index: 303979 (C4 (Web Text))

Max Activating Token Index: 840

Text #17

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0257. Min Act: -0.0002

Data Index: 330537 (C4 (Web Text))

Max Activating Token Index: 882

Text #18

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0258. Min Act: -0.0002

Data Index: 106931 (C4 (Web Text))

Max Activating Token Index: 164

Text #19

Max Range: 0.0380. Min Range: -0.0380

Max Act: 0.0254. Min Act: -0.0002

Data Index: 936433 (C4 (Web Text))

Max Activating Token Index: 1002