Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2860 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0394. Min Act: -0.0003

Data Index: 118778 (C4 (Web Text))

Max Activating Token Index: 828

Text #1

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0393. Min Act: -0.0003

Data Index: 1461257 (Python Code)

Max Activating Token Index: 200

Text #2

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0344. Min Act: -0.0003

Data Index: 60404 (C4 (Web Text))

Max Activating Token Index: 836

Text #3

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0385. Min Act: -0.0003

Data Index: 339084 (C4 (Web Text))

Max Activating Token Index: 791

Text #4

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0353. Min Act: -0.0003

Data Index: 947334 (C4 (Web Text))

Max Activating Token Index: 563

Text #5

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0343. Min Act: -0.0003

Data Index: 97275 (C4 (Web Text))

Max Activating Token Index: 780

Text #6

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0341. Min Act: -0.0003

Data Index: 44437 (C4 (Web Text))

Max Activating Token Index: 665

Text #7

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0354. Min Act: -0.0003

Data Index: 1092223 (C4 (Web Text))

Max Activating Token Index: 73

Text #8

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0358. Min Act: -0.0003

Data Index: 1602711 (Python Code)

Max Activating Token Index: 69

Text #9

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0326. Min Act: -0.0003

Data Index: 935188 (C4 (Web Text))

Max Activating Token Index: 494

Text #10

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0338. Min Act: -0.0003

Data Index: 1354940 (C4 (Web Text))

Max Activating Token Index: 19

Text #11

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0372. Min Act: -0.0003

Data Index: 273389 (C4 (Web Text))

Max Activating Token Index: 638

Text #12

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0330. Min Act: -0.0003

Data Index: 342361 (C4 (Web Text))

Max Activating Token Index: 532

Text #13

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0320. Min Act: -0.0003

Data Index: 1082867 (C4 (Web Text))

Max Activating Token Index: 949

Text #14

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0330. Min Act: -0.0003

Data Index: 275354 (C4 (Web Text))

Max Activating Token Index: 16

Text #15

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0351. Min Act: -0.0003

Data Index: 490588 (C4 (Web Text))

Max Activating Token Index: 720

Text #16

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0314. Min Act: -0.0003

Data Index: 36976 (C4 (Web Text))

Max Activating Token Index: 126

Text #17

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0371. Min Act: -0.0003

Data Index: 225873 (C4 (Web Text))

Max Activating Token Index: 617

Text #18

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0338. Min Act: -0.0003

Data Index: 549232 (C4 (Web Text))

Max Activating Token Index: 573

Text #19

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0300. Min Act: -0.0003

Data Index: 1561215 (Python Code)

Max Activating Token Index: 11