Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4021 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0314. Min Act: -0.0002

Data Index: 322245 (C4 (Web Text))

Max Activating Token Index: 49

Text #1

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0297. Min Act: -0.0002

Data Index: 1424860 (Python Code)

Max Activating Token Index: 781

Text #2

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0284. Min Act: -0.0002

Data Index: 1612508 (Python Code)

Max Activating Token Index: 755

Text #3

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0288. Min Act: -0.0002

Data Index: 222472 (C4 (Web Text))

Max Activating Token Index: 578

Text #4

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0283. Min Act: -0.0002

Data Index: 1383274 (Python Code)

Max Activating Token Index: 222

Text #5

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0292. Min Act: -0.0002

Data Index: 898544 (C4 (Web Text))

Max Activating Token Index: 449

Text #6

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0286. Min Act: -0.0002

Data Index: 260818 (C4 (Web Text))

Max Activating Token Index: 661

Text #7

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0284. Min Act: -0.0002

Data Index: 1491226 (Python Code)

Max Activating Token Index: 858

Text #8

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0282. Min Act: -0.0002

Data Index: 213670 (C4 (Web Text))

Max Activating Token Index: 755

Text #9

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0274. Min Act: -0.0002

Data Index: 1359294 (C4 (Web Text))

Max Activating Token Index: 546

Text #10

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0277. Min Act: -0.0002

Data Index: 1430726 (Python Code)

Max Activating Token Index: 880

Text #11

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0272. Min Act: -0.0002

Data Index: 1517973 (Python Code)

Max Activating Token Index: 547

Text #12

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0266. Min Act: -0.0002

Data Index: 1176367 (C4 (Web Text))

Max Activating Token Index: 730

Text #13

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0270. Min Act: -0.0002

Data Index: 304119 (C4 (Web Text))

Max Activating Token Index: 431

Text #14

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0270. Min Act: -0.0002

Data Index: 1588164 (Python Code)

Max Activating Token Index: 277

Text #15

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0269. Min Act: -0.0002

Data Index: 521108 (C4 (Web Text))

Max Activating Token Index: 571

Text #16

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0268. Min Act: -0.0002

Data Index: 1465603 (Python Code)

Max Activating Token Index: 536

Text #17

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0266. Min Act: -0.0002

Data Index: 547775 (C4 (Web Text))

Max Activating Token Index: 228

Text #18

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0263. Min Act: -0.0002

Data Index: 18979 (C4 (Web Text))

Max Activating Token Index: 555

Text #19

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0262. Min Act: -0.0002

Data Index: 1498785 (Python Code)

Max Activating Token Index: 13