Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 461 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0408. Min Range: -0.0408

Max Act: 0.0408. Min Act: -0.0005

Data Index: 206887 (C4 (Web Text))

Max Activating Token Index: 893

Text #1

Max Range: 0.0408. Min Range: -0.0408

Max Act: 0.0271. Min Act: -0.0005

Data Index: 1529104 (Python Code)

Max Activating Token Index: 523

Text #2

Max Range: 0.0408. Min Range: -0.0408

Max Act: 0.0280. Min Act: -0.0005

Data Index: 1120992 (C4 (Web Text))

Max Activating Token Index: 588

Text #3

Max Range: 0.0408. Min Range: -0.0408

Max Act: 0.0286. Min Act: -0.0005

Data Index: 1417957 (Python Code)

Max Activating Token Index: 385

Text #4

Max Range: 0.0408. Min Range: -0.0408

Max Act: 0.0273. Min Act: -0.0005

Data Index: 1507929 (Python Code)

Max Activating Token Index: 704

Text #5

Max Range: 0.0408. Min Range: -0.0408

Max Act: 0.0244. Min Act: -0.0005

Data Index: 1494776 (Python Code)

Max Activating Token Index: 616

Text #6

Max Range: 0.0408. Min Range: -0.0408

Max Act: 0.0253. Min Act: -0.0005

Data Index: 380801 (C4 (Web Text))

Max Activating Token Index: 79

Text #7

Max Range: 0.0408. Min Range: -0.0408

Max Act: 0.0252. Min Act: -0.0005

Data Index: 1487862 (Python Code)

Max Activating Token Index: 483

Text #8

Max Range: 0.0408. Min Range: -0.0408

Max Act: 0.0254. Min Act: -0.0005

Data Index: 1409673 (Python Code)

Max Activating Token Index: 35

Text #9

Max Range: 0.0408. Min Range: -0.0408

Max Act: 0.0248. Min Act: -0.0005

Data Index: 1512191 (Python Code)

Max Activating Token Index: 842

Text #10

Max Range: 0.0408. Min Range: -0.0408

Max Act: 0.0255. Min Act: -0.0005

Data Index: 1373540 (Python Code)

Max Activating Token Index: 213

Text #11

Max Range: 0.0408. Min Range: -0.0408

Max Act: 0.0256. Min Act: -0.0005

Data Index: 1435218 (Python Code)

Max Activating Token Index: 44

Text #12

Max Range: 0.0408. Min Range: -0.0408

Max Act: 0.0244. Min Act: -0.0005

Data Index: 1527432 (Python Code)

Max Activating Token Index: 545

Text #13

Max Range: 0.0408. Min Range: -0.0408

Max Act: 0.0255. Min Act: -0.0005

Data Index: 1611348 (Python Code)

Max Activating Token Index: 46

Text #14

Max Range: 0.0408. Min Range: -0.0408

Max Act: 0.0248. Min Act: -0.0005

Data Index: 395627 (C4 (Web Text))

Max Activating Token Index: 194

Text #15

Max Range: 0.0408. Min Range: -0.0408

Max Act: 0.0246. Min Act: -0.0005

Data Index: 1434358 (Python Code)

Max Activating Token Index: 70

Text #16

Max Range: 0.0408. Min Range: -0.0408

Max Act: 0.0240. Min Act: -0.0005

Data Index: 1583078 (Python Code)

Max Activating Token Index: 29

Text #17

Max Range: 0.0408. Min Range: -0.0408

Max Act: 0.0223. Min Act: -0.0005

Data Index: 401226 (C4 (Web Text))

Max Activating Token Index: 391

Text #18

Max Range: 0.0408. Min Range: -0.0408

Max Act: 0.0241. Min Act: -0.0005

Data Index: 528130 (C4 (Web Text))

Max Activating Token Index: 618

Text #19

Max Range: 0.0408. Min Range: -0.0408

Max Act: 0.0242. Min Act: -0.0005

Data Index: 836845 (C4 (Web Text))

Max Activating Token Index: 684