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

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

Neuron 4197 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0494. Min Act: -0.0000

Data Index: 288132 (C4 (Web Text))

Max Activating Token Index: 422

Text #1

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0370. Min Act: -0.0000

Data Index: 475883 (C4 (Web Text))

Max Activating Token Index: 344

Text #2

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0417. Min Act: -0.0000

Data Index: 376556 (C4 (Web Text))

Max Activating Token Index: 798

Text #3

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0334. Min Act: -0.0000

Data Index: 401316 (C4 (Web Text))

Max Activating Token Index: 337

Text #4

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0347. Min Act: -0.0000

Data Index: 1418643 (Python Code)

Max Activating Token Index: 317

Text #5

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0380. Min Act: -0.0000

Data Index: 216585 (C4 (Web Text))

Max Activating Token Index: 775

Text #6

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0300. Min Act: -0.0000

Data Index: 1458511 (Python Code)

Max Activating Token Index: 353

Text #7

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0308. Min Act: -0.0000

Data Index: 175897 (C4 (Web Text))

Max Activating Token Index: 971

Text #8

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0431. Min Act: -0.0000

Data Index: 542533 (C4 (Web Text))

Max Activating Token Index: 372

Text #9

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0349. Min Act: -0.0000

Data Index: 598567 (C4 (Web Text))

Max Activating Token Index: 649

Text #10

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0329. Min Act: -0.0000

Data Index: 1444463 (Python Code)

Max Activating Token Index: 807

Text #11

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0297. Min Act: -0.0000

Data Index: 1404867 (Python Code)

Max Activating Token Index: 259

Text #12

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0279. Min Act: -0.0000

Data Index: 1381725 (Python Code)

Max Activating Token Index: 596

Text #13

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0265. Min Act: -0.0000

Data Index: 1386894 (Python Code)

Max Activating Token Index: 127

Text #14

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0316. Min Act: -0.0000

Data Index: 861066 (C4 (Web Text))

Max Activating Token Index: 663

Text #15

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0305. Min Act: -0.0000

Data Index: 202493 (C4 (Web Text))

Max Activating Token Index: 822

Text #16

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0307. Min Act: -0.0000

Data Index: 571862 (C4 (Web Text))

Max Activating Token Index: 811

Text #17

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0268. Min Act: -0.0000

Data Index: 1369719 (Python Code)

Max Activating Token Index: 1004

Text #18

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0259. Min Act: -0.0000

Data Index: 1621938 (Python Code)

Max Activating Token Index: 97

Text #19

Max Range: 0.0494. Min Range: -0.0494

Max Act: 0.0290. Min Act: -0.0000

Data Index: 1557850 (Python Code)

Max Activating Token Index: 281