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

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

Neuron 665 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: 0.0362. Min Range: -0.0362

Max Act: 0.0362. Min Act: -0.0004

Data Index: 366348 (C4 (Web Text))

Max Activating Token Index: 689

Text #1

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0330. Min Act: -0.0005

Data Index: 419552 (C4 (Web Text))

Max Activating Token Index: 948

Text #2

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0310. Min Act: -0.0005

Data Index: 638290 (C4 (Web Text))

Max Activating Token Index: 43

Text #3

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0301. Min Act: -0.0005

Data Index: 435709 (C4 (Web Text))

Max Activating Token Index: 323

Text #4

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0291. Min Act: -0.0005

Data Index: 749905 (C4 (Web Text))

Max Activating Token Index: 86

Text #5

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0279. Min Act: -0.0005

Data Index: 1327612 (C4 (Web Text))

Max Activating Token Index: 908

Text #6

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0282. Min Act: -0.0005

Data Index: 18299 (C4 (Web Text))

Max Activating Token Index: 110

Text #7

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0263. Min Act: -0.0005

Data Index: 1638095 (Python Code)

Max Activating Token Index: 389

Text #8

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0263. Min Act: -0.0005

Data Index: 1123697 (C4 (Web Text))

Max Activating Token Index: 439

Text #9

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0267. Min Act: -0.0005

Data Index: 680449 (C4 (Web Text))

Max Activating Token Index: 566

Text #10

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0266. Min Act: -0.0005

Data Index: 666795 (C4 (Web Text))

Max Activating Token Index: 791

Text #11

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0276. Min Act: -0.0005

Data Index: 598355 (C4 (Web Text))

Max Activating Token Index: 83

Text #12

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0264. Min Act: -0.0005

Data Index: 505259 (C4 (Web Text))

Max Activating Token Index: 437

Text #13

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0257. Min Act: -0.0005

Data Index: 320922 (C4 (Web Text))

Max Activating Token Index: 186

Text #14

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0267. Min Act: -0.0005

Data Index: 172978 (C4 (Web Text))

Max Activating Token Index: 327

Text #15

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0259. Min Act: -0.0005

Data Index: 1526597 (Python Code)

Max Activating Token Index: 953

Text #16

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0249. Min Act: -0.0005

Data Index: 1209810 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0255. Min Act: -0.0005

Data Index: 909677 (C4 (Web Text))

Max Activating Token Index: 548

Text #18

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0255. Min Act: -0.0005

Data Index: 1488180 (Python Code)

Max Activating Token Index: 995

Text #19

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0254. Min Act: -0.0005

Data Index: 124273 (C4 (Web Text))

Max Activating Token Index: 1023