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

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

Neuron 1187 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: 0.0292. Min Range: -0.0292

Max Act: 0.0286. Min Act: -0.0005

Data Index: 1402717 (Python Code)

Max Activating Token Index: 746

Text #1

Max Range: 0.0292. Min Range: -0.0292

Max Act: 0.0278. Min Act: -0.0005

Data Index: 578108 (C4 (Web Text))

Max Activating Token Index: 838

Text #2

Max Range: 0.0292. Min Range: -0.0292

Max Act: 0.0292. Min Act: -0.0005

Data Index: 1388093 (Python Code)

Max Activating Token Index: 551

Text #3

Max Range: 0.0292. Min Range: -0.0292

Max Act: 0.0286. Min Act: -0.0005

Data Index: 1559425 (Python Code)

Max Activating Token Index: 676

Text #4

Max Range: 0.0292. Min Range: -0.0292

Max Act: 0.0274. Min Act: -0.0005

Data Index: 1197014 (C4 (Web Text))

Max Activating Token Index: 621

Text #5

Max Range: 0.0292. Min Range: -0.0292

Max Act: 0.0287. Min Act: -0.0005

Data Index: 375710 (C4 (Web Text))

Max Activating Token Index: 460

Text #6

Max Range: 0.0292. Min Range: -0.0292

Max Act: 0.0280. Min Act: -0.0005

Data Index: 591836 (C4 (Web Text))

Max Activating Token Index: 27

Text #7

Max Range: 0.0292. Min Range: -0.0292

Max Act: 0.0276. Min Act: -0.0005

Data Index: 716886 (C4 (Web Text))

Max Activating Token Index: 874

Text #8

Max Range: 0.0292. Min Range: -0.0292

Max Act: 0.0277. Min Act: -0.0005

Data Index: 876674 (C4 (Web Text))

Max Activating Token Index: 821

Text #9

Max Range: 0.0292. Min Range: -0.0292

Max Act: 0.0288. Min Act: -0.0005

Data Index: 440820 (C4 (Web Text))

Max Activating Token Index: 399

Text #10

Max Range: 0.0292. Min Range: -0.0292

Max Act: 0.0274. Min Act: -0.0005

Data Index: 728649 (C4 (Web Text))

Max Activating Token Index: 798

Text #11

Max Range: 0.0292. Min Range: -0.0292

Max Act: 0.0269. Min Act: -0.0005

Data Index: 1473019 (Python Code)

Max Activating Token Index: 44

Text #12

Max Range: 0.0292. Min Range: -0.0292

Max Act: 0.0274. Min Act: -0.0005

Data Index: 1162578 (C4 (Web Text))

Max Activating Token Index: 441

Text #13

Max Range: 0.0292. Min Range: -0.0292

Max Act: 0.0273. Min Act: -0.0005

Data Index: 854480 (C4 (Web Text))

Max Activating Token Index: 521

Text #14

Max Range: 0.0292. Min Range: -0.0292

Max Act: 0.0274. Min Act: -0.0005

Data Index: 198295 (C4 (Web Text))

Max Activating Token Index: 888

Text #15

Max Range: 0.0292. Min Range: -0.0292

Max Act: 0.0266. Min Act: -0.0005

Data Index: 943568 (C4 (Web Text))

Max Activating Token Index: 871

Text #16

Max Range: 0.0292. Min Range: -0.0292

Max Act: 0.0279. Min Act: -0.0005

Data Index: 1034630 (C4 (Web Text))

Max Activating Token Index: 113

Text #17

Max Range: 0.0292. Min Range: -0.0292

Max Act: 0.0273. Min Act: -0.0005

Data Index: 355129 (C4 (Web Text))

Max Activating Token Index: 535

Text #18

Max Range: 0.0292. Min Range: -0.0292

Max Act: 0.0261. Min Act: -0.0005

Data Index: 388837 (C4 (Web Text))

Max Activating Token Index: 333

Text #19

Max Range: 0.0292. Min Range: -0.0292

Max Act: 0.0267. Min Act: -0.0005

Data Index: 1447609 (Python Code)

Max Activating Token Index: 24