Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 950 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0386. Min Act: -0.0003

Data Index: 787116 (C4 (Web Text))

Max Activating Token Index: 368

Text #1

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0336. Min Act: -0.0003

Data Index: 111384 (C4 (Web Text))

Max Activating Token Index: 152

Text #2

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0340. Min Act: -0.0003

Data Index: 1015280 (C4 (Web Text))

Max Activating Token Index: 638

Text #3

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0343. Min Act: -0.0003

Data Index: 962789 (C4 (Web Text))

Max Activating Token Index: 31

Text #4

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0366. Min Act: -0.0003

Data Index: 493216 (C4 (Web Text))

Max Activating Token Index: 607

Text #5

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0304. Min Act: -0.0003

Data Index: 172620 (C4 (Web Text))

Max Activating Token Index: 587

Text #6

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0301. Min Act: -0.0003

Data Index: 816956 (C4 (Web Text))

Max Activating Token Index: 1011

Text #7

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0280. Min Act: -0.0003

Data Index: 265133 (C4 (Web Text))

Max Activating Token Index: 860

Text #8

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0323. Min Act: -0.0003

Data Index: 1419464 (Python Code)

Max Activating Token Index: 1016

Text #9

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0303. Min Act: -0.0003

Data Index: 1001198 (C4 (Web Text))

Max Activating Token Index: 353

Text #10

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0315. Min Act: -0.0003

Data Index: 59242 (C4 (Web Text))

Max Activating Token Index: 42

Text #11

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0296. Min Act: -0.0003

Data Index: 666700 (C4 (Web Text))

Max Activating Token Index: 671

Text #12

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0302. Min Act: -0.0003

Data Index: 1622210 (Python Code)

Max Activating Token Index: 744

Text #13

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0276. Min Act: -0.0003

Data Index: 1374914 (Python Code)

Max Activating Token Index: 637

Text #14

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0306. Min Act: -0.0003

Data Index: 320768 (C4 (Web Text))

Max Activating Token Index: 838

Text #15

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0303. Min Act: -0.0003

Data Index: 99850 (C4 (Web Text))

Max Activating Token Index: 71

Text #16

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0287. Min Act: -0.0003

Data Index: 1502333 (Python Code)

Max Activating Token Index: 726

Text #17

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0253. Min Act: -0.0003

Data Index: 1225597 (C4 (Web Text))

Max Activating Token Index: 380

Text #18

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0311. Min Act: -0.0003

Data Index: 747871 (C4 (Web Text))

Max Activating Token Index: 722

Text #19

Max Range: 0.0386. Min Range: -0.0386

Max Act: 0.0287. Min Act: -0.0003

Data Index: 777376 (C4 (Web Text))

Max Activating Token Index: 623