Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 458 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0426. Min Range: -0.0426

Max Act: 0.0417. Min Act: -0.0003

Data Index: 146666 (C4 (Web Text))

Max Activating Token Index: 249

Text #1

Max Range: 0.0426. Min Range: -0.0426

Max Act: 0.0426. Min Act: -0.0003

Data Index: 353089 (C4 (Web Text))

Max Activating Token Index: 335

Text #2

Max Range: 0.0426. Min Range: -0.0426

Max Act: 0.0385. Min Act: -0.0003

Data Index: 262926 (C4 (Web Text))

Max Activating Token Index: 11

Text #3

Max Range: 0.0426. Min Range: -0.0426

Max Act: 0.0362. Min Act: -0.0003

Data Index: 855546 (C4 (Web Text))

Max Activating Token Index: 573

Text #4

Max Range: 0.0426. Min Range: -0.0426

Max Act: 0.0368. Min Act: -0.0003

Data Index: 785950 (C4 (Web Text))

Max Activating Token Index: 495

Text #5

Max Range: 0.0426. Min Range: -0.0426

Max Act: 0.0353. Min Act: -0.0003

Data Index: 92242 (C4 (Web Text))

Max Activating Token Index: 107

Text #6

Max Range: 0.0426. Min Range: -0.0426

Max Act: 0.0341. Min Act: -0.0004

Data Index: 291550 (C4 (Web Text))

Max Activating Token Index: 302

Text #7

Max Range: 0.0426. Min Range: -0.0426

Max Act: 0.0352. Min Act: -0.0003

Data Index: 955262 (C4 (Web Text))

Max Activating Token Index: 441

Text #8

Max Range: 0.0426. Min Range: -0.0426

Max Act: 0.0329. Min Act: -0.0003

Data Index: 659205 (C4 (Web Text))

Max Activating Token Index: 818

Text #9

Max Range: 0.0426. Min Range: -0.0426

Max Act: 0.0325. Min Act: -0.0003

Data Index: 650148 (C4 (Web Text))

Max Activating Token Index: 564

Text #10

Max Range: 0.0426. Min Range: -0.0426

Max Act: 0.0321. Min Act: -0.0003

Data Index: 571235 (C4 (Web Text))

Max Activating Token Index: 1000

Text #11

Max Range: 0.0426. Min Range: -0.0426

Max Act: 0.0325. Min Act: -0.0003

Data Index: 1064516 (C4 (Web Text))

Max Activating Token Index: 572

Text #12

Max Range: 0.0426. Min Range: -0.0426

Max Act: 0.0332. Min Act: -0.0003

Data Index: 1220772 (C4 (Web Text))

Max Activating Token Index: 206

Text #13

Max Range: 0.0426. Min Range: -0.0426

Max Act: 0.0322. Min Act: -0.0003

Data Index: 1253474 (C4 (Web Text))

Max Activating Token Index: 93

Text #14

Max Range: 0.0426. Min Range: -0.0426

Max Act: 0.0330. Min Act: -0.0003

Data Index: 1021924 (C4 (Web Text))

Max Activating Token Index: 536

Text #15

Max Range: 0.0426. Min Range: -0.0426

Max Act: 0.0317. Min Act: -0.0003

Data Index: 979707 (C4 (Web Text))

Max Activating Token Index: 40

Text #16

Max Range: 0.0426. Min Range: -0.0426

Max Act: 0.0335. Min Act: -0.0003

Data Index: 549760 (C4 (Web Text))

Max Activating Token Index: 172

Text #17

Max Range: 0.0426. Min Range: -0.0426

Max Act: 0.0319. Min Act: -0.0004

Data Index: 375458 (C4 (Web Text))

Max Activating Token Index: 347

Text #18

Max Range: 0.0426. Min Range: -0.0426

Max Act: 0.0303. Min Act: -0.0003

Data Index: 1207618 (C4 (Web Text))

Max Activating Token Index: 740

Text #19

Max Range: 0.0426. Min Range: -0.0426

Max Act: 0.0313. Min Act: -0.0003

Data Index: 942276 (C4 (Web Text))

Max Activating Token Index: 235