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

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

Neuron 598 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0319. Min Act: -0.0006

Data Index: 128036 (C4 (Web Text))

Max Activating Token Index: 50

Text #1

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0323. Min Act: -0.0006

Data Index: 309786 (C4 (Web Text))

Max Activating Token Index: 42

Text #2

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0320. Min Act: -0.0006

Data Index: 801253 (C4 (Web Text))

Max Activating Token Index: 125

Text #3

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0314. Min Act: -0.0006

Data Index: 577923 (C4 (Web Text))

Max Activating Token Index: 409

Text #4

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0292. Min Act: -0.0006

Data Index: 1280009 (C4 (Web Text))

Max Activating Token Index: 870

Text #5

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0299. Min Act: -0.0006

Data Index: 174758 (C4 (Web Text))

Max Activating Token Index: 99

Text #6

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0299. Min Act: -0.0006

Data Index: 201466 (C4 (Web Text))

Max Activating Token Index: 244

Text #7

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0296. Min Act: -0.0006

Data Index: 1501062 (Python Code)

Max Activating Token Index: 825

Text #8

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0287. Min Act: -0.0006

Data Index: 36537 (C4 (Web Text))

Max Activating Token Index: 412

Text #9

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0286. Min Act: -0.0006

Data Index: 1086393 (C4 (Web Text))

Max Activating Token Index: 750

Text #10

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0290. Min Act: -0.0006

Data Index: 1242221 (C4 (Web Text))

Max Activating Token Index: 1022

Text #11

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0287. Min Act: -0.0006

Data Index: 425926 (C4 (Web Text))

Max Activating Token Index: 307

Text #12

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0283. Min Act: -0.0006

Data Index: 1141782 (C4 (Web Text))

Max Activating Token Index: 31

Text #13

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0274. Min Act: -0.0006

Data Index: 525824 (C4 (Web Text))

Max Activating Token Index: 412

Text #14

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0280. Min Act: -0.0006

Data Index: 607202 (C4 (Web Text))

Max Activating Token Index: 617

Text #15

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0291. Min Act: -0.0006

Data Index: 844676 (C4 (Web Text))

Max Activating Token Index: 517

Text #16

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0273. Min Act: -0.0006

Data Index: 1074795 (C4 (Web Text))

Max Activating Token Index: 734

Text #17

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0276. Min Act: -0.0006

Data Index: 185888 (C4 (Web Text))

Max Activating Token Index: 185

Text #18

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0271. Min Act: -0.0006

Data Index: 602064 (C4 (Web Text))

Max Activating Token Index: 449

Text #19

Max Range: 0.0323. Min Range: -0.0323

Max Act: 0.0284. Min Act: -0.0006

Data Index: 1092957 (C4 (Web Text))

Max Activating Token Index: 881