Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3593 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0458. Min Act: -0.0002

Data Index: 719546 (C4 (Web Text))

Max Activating Token Index: 34

Text #1

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0427. Min Act: -0.0002

Data Index: 218055 (C4 (Web Text))

Max Activating Token Index: 100

Text #2

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0425. Min Act: -0.0002

Data Index: 414794 (C4 (Web Text))

Max Activating Token Index: 348

Text #3

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0405. Min Act: -0.0002

Data Index: 276507 (C4 (Web Text))

Max Activating Token Index: 772

Text #4

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0400. Min Act: -0.0002

Data Index: 885502 (C4 (Web Text))

Max Activating Token Index: 309

Text #5

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0397. Min Act: -0.0002

Data Index: 839739 (C4 (Web Text))

Max Activating Token Index: 105

Text #6

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0398. Min Act: -0.0002

Data Index: 299835 (C4 (Web Text))

Max Activating Token Index: 771

Text #7

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0346. Min Act: -0.0002

Data Index: 415537 (C4 (Web Text))

Max Activating Token Index: 733

Text #8

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0365. Min Act: -0.0002

Data Index: 1187071 (C4 (Web Text))

Max Activating Token Index: 339

Text #9

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0335. Min Act: -0.0002

Data Index: 271650 (C4 (Web Text))

Max Activating Token Index: 50

Text #10

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0327. Min Act: -0.0002

Data Index: 470913 (C4 (Web Text))

Max Activating Token Index: 900

Text #11

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0336. Min Act: -0.0002

Data Index: 1055109 (C4 (Web Text))

Max Activating Token Index: 604

Text #12

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0319. Min Act: -0.0002

Data Index: 350473 (C4 (Web Text))

Max Activating Token Index: 556

Text #13

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0325. Min Act: -0.0002

Data Index: 433589 (C4 (Web Text))

Max Activating Token Index: 725

Text #14

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0318. Min Act: -0.0002

Data Index: 1265626 (C4 (Web Text))

Max Activating Token Index: 545

Text #15

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0299. Min Act: -0.0002

Data Index: 1011178 (C4 (Web Text))

Max Activating Token Index: 866

Text #16

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0311. Min Act: -0.0002

Data Index: 864706 (C4 (Web Text))

Max Activating Token Index: 765

Text #17

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0313. Min Act: -0.0002

Data Index: 628356 (C4 (Web Text))

Max Activating Token Index: 853

Text #18

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0300. Min Act: -0.0002

Data Index: 1198569 (C4 (Web Text))

Max Activating Token Index: 955

Text #19

Max Range: 0.0458. Min Range: -0.0458

Max Act: 0.0295. Min Act: -0.0002

Data Index: 935792 (C4 (Web Text))

Max Activating Token Index: 882