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

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

Neuron 184 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: 0.0536. Min Range: -0.0536

Max Act: 0.0536. Min Act: -0.0002

Data Index: 196218 (C4 (Web Text))

Max Activating Token Index: 825

Text #1

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0493. Min Act: -0.0002

Data Index: 1314744 (C4 (Web Text))

Max Activating Token Index: 876

Text #2

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0466. Min Act: -0.0002

Data Index: 395045 (C4 (Web Text))

Max Activating Token Index: 150

Text #3

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0459. Min Act: -0.0002

Data Index: 502906 (C4 (Web Text))

Max Activating Token Index: 953

Text #4

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0478. Min Act: -0.0002

Data Index: 28975 (C4 (Web Text))

Max Activating Token Index: 254

Text #5

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0401. Min Act: -0.0002

Data Index: 1618731 (Python Code)

Max Activating Token Index: 72

Text #6

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0392. Min Act: -0.0002

Data Index: 1654280 (Python Code)

Max Activating Token Index: 149

Text #7

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0331. Min Act: -0.0002

Data Index: 597841 (C4 (Web Text))

Max Activating Token Index: 752

Text #8

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0369. Min Act: -0.0002

Data Index: 882862 (C4 (Web Text))

Max Activating Token Index: 229

Text #9

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0318. Min Act: -0.0002

Data Index: 1517571 (Python Code)

Max Activating Token Index: 204

Text #10

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0319. Min Act: -0.0002

Data Index: 157981 (C4 (Web Text))

Max Activating Token Index: 103

Text #11

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0358. Min Act: -0.0002

Data Index: 799493 (C4 (Web Text))

Max Activating Token Index: 293

Text #12

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0291. Min Act: -0.0002

Data Index: 1362779 (Python Code)

Max Activating Token Index: 331

Text #13

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0296. Min Act: -0.0002

Data Index: 416036 (C4 (Web Text))

Max Activating Token Index: 91

Text #14

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0269. Min Act: -0.0002

Data Index: 1513833 (Python Code)

Max Activating Token Index: 351

Text #15

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0258. Min Act: -0.0002

Data Index: 1201620 (C4 (Web Text))

Max Activating Token Index: 805

Text #16

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0279. Min Act: -0.0002

Data Index: 1536585 (Python Code)

Max Activating Token Index: 370

Text #17

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0285. Min Act: -0.0002

Data Index: 1503027 (Python Code)

Max Activating Token Index: 238

Text #18

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0284. Min Act: -0.0002

Data Index: 1586419 (Python Code)

Max Activating Token Index: 275

Text #19

Max Range: 0.0536. Min Range: -0.0536

Max Act: 0.0288. Min Act: -0.0002

Data Index: 1627914 (Python Code)

Max Activating Token Index: 225