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

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

Neuron 4128 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0420. Min Act: -0.0003

Data Index: 470239 (C4 (Web Text))

Max Activating Token Index: 877

Text #1

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0322. Min Act: -0.0003

Data Index: 1331468 (C4 (Web Text))

Max Activating Token Index: 279

Text #2

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0307. Min Act: -0.0002

Data Index: 670399 (C4 (Web Text))

Max Activating Token Index: 964

Text #3

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0302. Min Act: -0.0003

Data Index: 173120 (C4 (Web Text))

Max Activating Token Index: 287

Text #4

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0303. Min Act: -0.0002

Data Index: 679974 (C4 (Web Text))

Max Activating Token Index: 409

Text #5

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0309. Min Act: -0.0003

Data Index: 694836 (C4 (Web Text))

Max Activating Token Index: 94

Text #6

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0305. Min Act: -0.0003

Data Index: 923521 (C4 (Web Text))

Max Activating Token Index: 91

Text #7

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0298. Min Act: -0.0002

Data Index: 238411 (C4 (Web Text))

Max Activating Token Index: 529

Text #8

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0292. Min Act: -0.0003

Data Index: 318434 (C4 (Web Text))

Max Activating Token Index: 34

Text #9

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0289. Min Act: -0.0002

Data Index: 560498 (C4 (Web Text))

Max Activating Token Index: 371

Text #10

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0277. Min Act: -0.0003

Data Index: 425498 (C4 (Web Text))

Max Activating Token Index: 337

Text #11

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0296. Min Act: -0.0003

Data Index: 191389 (C4 (Web Text))

Max Activating Token Index: 585

Text #12

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0276. Min Act: -0.0003

Data Index: 958965 (C4 (Web Text))

Max Activating Token Index: 945

Text #13

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0282. Min Act: -0.0003

Data Index: 648047 (C4 (Web Text))

Max Activating Token Index: 732

Text #14

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0273. Min Act: -0.0002

Data Index: 1279323 (C4 (Web Text))

Max Activating Token Index: 460

Text #15

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0275. Min Act: -0.0002

Data Index: 696896 (C4 (Web Text))

Max Activating Token Index: 832

Text #16

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0256. Min Act: -0.0003

Data Index: 322803 (C4 (Web Text))

Max Activating Token Index: 586

Text #17

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0273. Min Act: -0.0003

Data Index: 442279 (C4 (Web Text))

Max Activating Token Index: 87

Text #18

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0271. Min Act: -0.0003

Data Index: 975506 (C4 (Web Text))

Max Activating Token Index: 40

Text #19

Max Range: 0.0420. Min Range: -0.0420

Max Act: 0.0275. Min Act: -0.0002

Data Index: 734039 (C4 (Web Text))

Max Activating Token Index: 579