Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3729 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0376. Min Act: -0.0001

Data Index: 1261646 (C4 (Web Text))

Max Activating Token Index: 689

Text #1

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0370. Min Act: -0.0002

Data Index: 218749 (C4 (Web Text))

Max Activating Token Index: 764

Text #2

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0342. Min Act: -0.0002

Data Index: 1026373 (C4 (Web Text))

Max Activating Token Index: 241

Text #3

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0348. Min Act: -0.0001

Data Index: 237713 (C4 (Web Text))

Max Activating Token Index: 570

Text #4

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0413. Min Act: -0.0002

Data Index: 1274261 (C4 (Web Text))

Max Activating Token Index: 261

Text #5

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0344. Min Act: -0.0002

Data Index: 1177517 (C4 (Web Text))

Max Activating Token Index: 456

Text #6

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0206. Min Act: -0.0002

Data Index: 84413 (C4 (Web Text))

Max Activating Token Index: 514

Text #7

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0356. Min Act: -0.0001

Data Index: 1006650 (C4 (Web Text))

Max Activating Token Index: 849

Text #8

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0339. Min Act: -0.0002

Data Index: 881762 (C4 (Web Text))

Max Activating Token Index: 379

Text #9

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0312. Min Act: -0.0002

Data Index: 674677 (C4 (Web Text))

Max Activating Token Index: 312

Text #10

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0322. Min Act: -0.0002

Data Index: 581857 (C4 (Web Text))

Max Activating Token Index: 337

Text #11

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0288. Min Act: -0.0002

Data Index: 1350817 (C4 (Web Text))

Max Activating Token Index: 274

Text #12

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0327. Min Act: -0.0002

Data Index: 830053 (C4 (Web Text))

Max Activating Token Index: 866

Text #13

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0292. Min Act: -0.0002

Data Index: 464754 (C4 (Web Text))

Max Activating Token Index: 680

Text #14

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0331. Min Act: -0.0002

Data Index: 348501 (C4 (Web Text))

Max Activating Token Index: 45

Text #15

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0318. Min Act: -0.0002

Data Index: 240498 (C4 (Web Text))

Max Activating Token Index: 215

Text #16

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0335. Min Act: -0.0001

Data Index: 1076618 (C4 (Web Text))

Max Activating Token Index: 968

Text #17

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0316. Min Act: -0.0001

Data Index: 667352 (C4 (Web Text))

Max Activating Token Index: 40

Text #18

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0297. Min Act: -0.0002

Data Index: 600188 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0279. Min Act: -0.0001

Data Index: 861256 (C4 (Web Text))

Max Activating Token Index: 661