Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5770 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0439. Min Act: -0.0002

Data Index: 58834 (C4 (Web Text))

Max Activating Token Index: 469

Text #1

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0434. Min Act: -0.0002

Data Index: 1341311 (C4 (Web Text))

Max Activating Token Index: 120

Text #2

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0358. Min Act: -0.0002

Data Index: 324419 (C4 (Web Text))

Max Activating Token Index: 594

Text #3

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0368. Min Act: -0.0002

Data Index: 435363 (C4 (Web Text))

Max Activating Token Index: 409

Text #4

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0342. Min Act: -0.0002

Data Index: 621329 (C4 (Web Text))

Max Activating Token Index: 782

Text #5

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0329. Min Act: -0.0002

Data Index: 253433 (C4 (Web Text))

Max Activating Token Index: 219

Text #6

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0328. Min Act: -0.0002

Data Index: 849647 (C4 (Web Text))

Max Activating Token Index: 96

Text #7

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0325. Min Act: -0.0002

Data Index: 1067706 (C4 (Web Text))

Max Activating Token Index: 930

Text #8

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0320. Min Act: -0.0002

Data Index: 510749 (C4 (Web Text))

Max Activating Token Index: 197

Text #9

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0313. Min Act: -0.0002

Data Index: 398520 (C4 (Web Text))

Max Activating Token Index: 31

Text #10

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0309. Min Act: -0.0002

Data Index: 894889 (C4 (Web Text))

Max Activating Token Index: 823

Text #11

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0314. Min Act: -0.0002

Data Index: 928731 (C4 (Web Text))

Max Activating Token Index: 417

Text #12

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0300. Min Act: -0.0002

Data Index: 578843 (C4 (Web Text))

Max Activating Token Index: 99

Text #13

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0295. Min Act: -0.0002

Data Index: 1220516 (C4 (Web Text))

Max Activating Token Index: 671

Text #14

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0302. Min Act: -0.0002

Data Index: 278972 (C4 (Web Text))

Max Activating Token Index: 415

Text #15

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0284. Min Act: -0.0002

Data Index: 135150 (C4 (Web Text))

Max Activating Token Index: 252

Text #16

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0280. Min Act: -0.0002

Data Index: 1031889 (C4 (Web Text))

Max Activating Token Index: 471

Text #17

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0278. Min Act: -0.0002

Data Index: 334813 (C4 (Web Text))

Max Activating Token Index: 632

Text #18

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0274. Min Act: -0.0002

Data Index: 1232195 (C4 (Web Text))

Max Activating Token Index: 273

Text #19

Max Range: 0.0439. Min Range: -0.0439

Max Act: 0.0273. Min Act: -0.0002

Data Index: 138963 (C4 (Web Text))

Max Activating Token Index: 263