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

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

Neuron 3616 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9377. Min Range: -1.9377

Max Act: 1.9377. Min Act: -0.0000

Data Index: 622080 (C4 (Web Text))

Max Activating Token Index: 557

Text #1

Max Range: 1.9377. Min Range: -1.9377

Max Act: 1.6214. Min Act: -0.0000

Data Index: 1623660 (Python Code)

Max Activating Token Index: 81

Text #2

Max Range: 1.9377. Min Range: -1.9377

Max Act: 1.6274. Min Act: -0.0000

Data Index: 1290270 (C4 (Web Text))

Max Activating Token Index: 556

Text #3

Max Range: 1.9377. Min Range: -1.9377

Max Act: 1.6619. Min Act: -0.0000

Data Index: 1164218 (C4 (Web Text))

Max Activating Token Index: 292

Text #4

Max Range: 1.9377. Min Range: -1.9377

Max Act: 1.5590. Min Act: -0.0000

Data Index: 1522627 (Python Code)

Max Activating Token Index: 365

Text #5

Max Range: 1.9377. Min Range: -1.9377

Max Act: 1.5028. Min Act: -0.0000

Data Index: 1538238 (Python Code)

Max Activating Token Index: 484

Text #6

Max Range: 1.9377. Min Range: -1.9377

Max Act: 1.3839. Min Act: -0.0000

Data Index: 713808 (C4 (Web Text))

Max Activating Token Index: 872

Text #7

Max Range: 1.9377. Min Range: -1.9377

Max Act: 1.5195. Min Act: -0.0000

Data Index: 832908 (C4 (Web Text))

Max Activating Token Index: 504

Text #8

Max Range: 1.9377. Min Range: -1.9377

Max Act: 1.3842. Min Act: -0.0000

Data Index: 1586748 (Python Code)

Max Activating Token Index: 27

Text #9

Max Range: 1.9377. Min Range: -1.9377

Max Act: 1.3955. Min Act: 0.0000

Data Index: 1582757 (Python Code)

Max Activating Token Index: 76

Text #10

Max Range: 1.9377. Min Range: -1.9377

Max Act: 1.3065. Min Act: -0.0000

Data Index: 1654384 (Python Code)

Max Activating Token Index: 296

Text #11

Max Range: 1.9377. Min Range: -1.9377

Max Act: 1.3741. Min Act: -0.0000

Data Index: 1380332 (Python Code)

Max Activating Token Index: 425

Text #12

Max Range: 1.9377. Min Range: -1.9377

Max Act: 1.4045. Min Act: -0.0000

Data Index: 969018 (C4 (Web Text))

Max Activating Token Index: 489

Text #13

Max Range: 1.9377. Min Range: -1.9377

Max Act: 1.3573. Min Act: -0.0000

Data Index: 1393734 (Python Code)

Max Activating Token Index: 205

Text #14

Max Range: 1.9377. Min Range: -1.9377

Max Act: 1.3464. Min Act: 0.0000

Data Index: 1465101 (Python Code)

Max Activating Token Index: 183

Text #15

Max Range: 1.9377. Min Range: -1.9377

Max Act: 1.3397. Min Act: -0.0000

Data Index: 1393796 (Python Code)

Max Activating Token Index: 792

Text #16

Max Range: 1.9377. Min Range: -1.9377

Max Act: 1.3262. Min Act: -0.0000

Data Index: 1557304 (Python Code)

Max Activating Token Index: 426

Text #17

Max Range: 1.9377. Min Range: -1.9377

Max Act: 1.3232. Min Act: -0.0000

Data Index: 1606838 (Python Code)

Max Activating Token Index: 336

Text #18

Max Range: 1.9377. Min Range: -1.9377

Max Act: 1.3527. Min Act: -0.0000

Data Index: 1441038 (Python Code)

Max Activating Token Index: 174

Text #19

Max Range: 1.9377. Min Range: -1.9377

Max Act: 1.3009. Min Act: -0.0000

Data Index: 1469801 (Python Code)

Max Activating Token Index: 386