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

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

Neuron 3111 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0457. Min Range: -0.0457

Max Act: 0.0446. Min Act: -0.0002

Data Index: 384036 (C4 (Web Text))

Max Activating Token Index: 731

Text #1

Max Range: 0.0457. Min Range: -0.0457

Max Act: 0.0457. Min Act: -0.0002

Data Index: 128907 (C4 (Web Text))

Max Activating Token Index: 232

Text #2

Max Range: 0.0457. Min Range: -0.0457

Max Act: 0.0433. Min Act: -0.0002

Data Index: 842067 (C4 (Web Text))

Max Activating Token Index: 474

Text #3

Max Range: 0.0457. Min Range: -0.0457

Max Act: 0.0405. Min Act: -0.0002

Data Index: 1195559 (C4 (Web Text))

Max Activating Token Index: 211

Text #4

Max Range: 0.0457. Min Range: -0.0457

Max Act: 0.0378. Min Act: -0.0002

Data Index: 404265 (C4 (Web Text))

Max Activating Token Index: 522

Text #5

Max Range: 0.0457. Min Range: -0.0457

Max Act: 0.0389. Min Act: -0.0002

Data Index: 783579 (C4 (Web Text))

Max Activating Token Index: 439

Text #6

Max Range: 0.0457. Min Range: -0.0457

Max Act: 0.0384. Min Act: -0.0002

Data Index: 1239497 (C4 (Web Text))

Max Activating Token Index: 557

Text #7

Max Range: 0.0457. Min Range: -0.0457

Max Act: 0.0346. Min Act: -0.0002

Data Index: 214056 (C4 (Web Text))

Max Activating Token Index: 60

Text #8

Max Range: 0.0457. Min Range: -0.0457

Max Act: 0.0355. Min Act: -0.0002

Data Index: 891261 (C4 (Web Text))

Max Activating Token Index: 115

Text #9

Max Range: 0.0457. Min Range: -0.0457

Max Act: 0.0374. Min Act: -0.0002

Data Index: 460392 (C4 (Web Text))

Max Activating Token Index: 807

Text #10

Max Range: 0.0457. Min Range: -0.0457

Max Act: 0.0351. Min Act: -0.0002

Data Index: 907355 (C4 (Web Text))

Max Activating Token Index: 280

Text #11

Max Range: 0.0457. Min Range: -0.0457

Max Act: 0.0360. Min Act: -0.0002

Data Index: 653721 (C4 (Web Text))

Max Activating Token Index: 808

Text #12

Max Range: 0.0457. Min Range: -0.0457

Max Act: 0.0319. Min Act: -0.0002

Data Index: 318630 (C4 (Web Text))

Max Activating Token Index: 665

Text #13

Max Range: 0.0457. Min Range: -0.0457

Max Act: 0.0339. Min Act: -0.0002

Data Index: 1053920 (C4 (Web Text))

Max Activating Token Index: 19

Text #14

Max Range: 0.0457. Min Range: -0.0457

Max Act: 0.0341. Min Act: -0.0002

Data Index: 126775 (C4 (Web Text))

Max Activating Token Index: 557

Text #15

Max Range: 0.0457. Min Range: -0.0457

Max Act: 0.0350. Min Act: -0.0002

Data Index: 605363 (C4 (Web Text))

Max Activating Token Index: 304

Text #16

Max Range: 0.0457. Min Range: -0.0457

Max Act: 0.0320. Min Act: -0.0002

Data Index: 185789 (C4 (Web Text))

Max Activating Token Index: 717

Text #17

Max Range: 0.0457. Min Range: -0.0457

Max Act: 0.0337. Min Act: -0.0002

Data Index: 1024148 (C4 (Web Text))

Max Activating Token Index: 350

Text #18

Max Range: 0.0457. Min Range: -0.0457

Max Act: 0.0322. Min Act: -0.0002

Data Index: 717471 (C4 (Web Text))

Max Activating Token Index: 10

Text #19

Max Range: 0.0457. Min Range: -0.0457

Max Act: 0.0280. Min Act: -0.0002

Data Index: 1296785 (C4 (Web Text))

Max Activating Token Index: 454