Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 2046 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0351. Min Act: -0.0003

Data Index: 717321 (C4 (Web Text))

Max Activating Token Index: 746

Text #1

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0342. Min Act: -0.0003

Data Index: 1433192 (Python Code)

Max Activating Token Index: 820

Text #2

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0320. Min Act: -0.0003

Data Index: 103609 (C4 (Web Text))

Max Activating Token Index: 432

Text #3

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0294. Min Act: -0.0003

Data Index: 61101 (C4 (Web Text))

Max Activating Token Index: 673

Text #4

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0297. Min Act: -0.0003

Data Index: 1289107 (C4 (Web Text))

Max Activating Token Index: 218

Text #5

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0289. Min Act: -0.0003

Data Index: 1135027 (C4 (Web Text))

Max Activating Token Index: 126

Text #6

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0293. Min Act: -0.0003

Data Index: 1494801 (Python Code)

Max Activating Token Index: 897

Text #7

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0290. Min Act: -0.0003

Data Index: 1509368 (Python Code)

Max Activating Token Index: 799

Text #8

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0260. Min Act: -0.0003

Data Index: 662475 (C4 (Web Text))

Max Activating Token Index: 242

Text #9

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0280. Min Act: -0.0003

Data Index: 1552759 (Python Code)

Max Activating Token Index: 964

Text #10

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0293. Min Act: -0.0003

Data Index: 913715 (C4 (Web Text))

Max Activating Token Index: 993

Text #11

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0273. Min Act: -0.0003

Data Index: 1643877 (Python Code)

Max Activating Token Index: 400

Text #12

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0269. Min Act: -0.0003

Data Index: 1622002 (Python Code)

Max Activating Token Index: 382

Text #13

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0274. Min Act: -0.0004

Data Index: 605676 (C4 (Web Text))

Max Activating Token Index: 796

Text #14

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0271. Min Act: -0.0003

Data Index: 495232 (C4 (Web Text))

Max Activating Token Index: 805

Text #15

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0245. Min Act: -0.0003

Data Index: 1308417 (C4 (Web Text))

Max Activating Token Index: 1005

Text #16

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0276. Min Act: -0.0003

Data Index: 1506378 (Python Code)

Max Activating Token Index: 916

Text #17

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0270. Min Act: -0.0003

Data Index: 1348646 (C4 (Web Text))

Max Activating Token Index: 487

Text #18

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0267. Min Act: -0.0003

Data Index: 323198 (C4 (Web Text))

Max Activating Token Index: 266

Text #19

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0280. Min Act: -0.0003

Data Index: 1394649 (Python Code)

Max Activating Token Index: 263