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

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

Neuron 85 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: 0.0475. Min Range: -0.0475

Max Act: 0.0475. Min Act: -0.0003

Data Index: 1055225 (C4 (Web Text))

Max Activating Token Index: 694

Text #1

Max Range: 0.0475. Min Range: -0.0475

Max Act: 0.0459. Min Act: -0.0003

Data Index: 349161 (C4 (Web Text))

Max Activating Token Index: 711

Text #2

Max Range: 0.0475. Min Range: -0.0475

Max Act: 0.0417. Min Act: -0.0002

Data Index: 47177 (C4 (Web Text))

Max Activating Token Index: 201

Text #3

Max Range: 0.0475. Min Range: -0.0475

Max Act: 0.0430. Min Act: -0.0003

Data Index: 299733 (C4 (Web Text))

Max Activating Token Index: 209

Text #4

Max Range: 0.0475. Min Range: -0.0475

Max Act: 0.0428. Min Act: -0.0003

Data Index: 1195589 (C4 (Web Text))

Max Activating Token Index: 536

Text #5

Max Range: 0.0475. Min Range: -0.0475

Max Act: 0.0410. Min Act: -0.0003

Data Index: 508387 (C4 (Web Text))

Max Activating Token Index: 503

Text #6

Max Range: 0.0475. Min Range: -0.0475

Max Act: 0.0405. Min Act: -0.0002

Data Index: 772287 (C4 (Web Text))

Max Activating Token Index: 795

Text #7

Max Range: 0.0475. Min Range: -0.0475

Max Act: 0.0397. Min Act: -0.0002

Data Index: 429452 (C4 (Web Text))

Max Activating Token Index: 925

Text #8

Max Range: 0.0475. Min Range: -0.0475

Max Act: 0.0399. Min Act: -0.0003

Data Index: 654511 (C4 (Web Text))

Max Activating Token Index: 814

Text #9

Max Range: 0.0475. Min Range: -0.0475

Max Act: 0.0364. Min Act: -0.0003

Data Index: 100467 (C4 (Web Text))

Max Activating Token Index: 231

Text #10

Max Range: 0.0475. Min Range: -0.0475

Max Act: 0.0383. Min Act: -0.0003

Data Index: 562770 (C4 (Web Text))

Max Activating Token Index: 64

Text #11

Max Range: 0.0475. Min Range: -0.0475

Max Act: 0.0370. Min Act: -0.0003

Data Index: 1246398 (C4 (Web Text))

Max Activating Token Index: 4

Text #12

Max Range: 0.0475. Min Range: -0.0475

Max Act: 0.0365. Min Act: -0.0002

Data Index: 147378 (C4 (Web Text))

Max Activating Token Index: 6

Text #13

Max Range: 0.0475. Min Range: -0.0475

Max Act: 0.0357. Min Act: -0.0003

Data Index: 1122510 (C4 (Web Text))

Max Activating Token Index: 66

Text #14

Max Range: 0.0475. Min Range: -0.0475

Max Act: 0.0362. Min Act: -0.0003

Data Index: 194802 (C4 (Web Text))

Max Activating Token Index: 293

Text #15

Max Range: 0.0475. Min Range: -0.0475

Max Act: 0.0367. Min Act: -0.0003

Data Index: 487415 (C4 (Web Text))

Max Activating Token Index: 907

Text #16

Max Range: 0.0475. Min Range: -0.0475

Max Act: 0.0356. Min Act: -0.0003

Data Index: 582537 (C4 (Web Text))

Max Activating Token Index: 702

Text #17

Max Range: 0.0475. Min Range: -0.0475

Max Act: 0.0338. Min Act: -0.0002

Data Index: 1079964 (C4 (Web Text))

Max Activating Token Index: 194

Text #18

Max Range: 0.0475. Min Range: -0.0475

Max Act: 0.0333. Min Act: -0.0003

Data Index: 413808 (C4 (Web Text))

Max Activating Token Index: 128

Text #19

Max Range: 0.0475. Min Range: -0.0475

Max Act: 0.0338. Min Act: -0.0003

Data Index: 1621558 (Python Code)

Max Activating Token Index: 209