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

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

Neuron 1692 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2592. Min Range: -0.2592

Max Act: 0.2417. Min Act: -0.0000

Data Index: 917613 (C4 (Web Text))

Max Activating Token Index: 498

Text #1

Max Range: 0.2592. Min Range: -0.2592

Max Act: 0.2592. Min Act: -0.0000

Data Index: 377062 (C4 (Web Text))

Max Activating Token Index: 203

Text #2

Max Range: 0.2592. Min Range: -0.2592

Max Act: 0.2546. Min Act: -0.0000

Data Index: 754073 (C4 (Web Text))

Max Activating Token Index: 985

Text #3

Max Range: 0.2592. Min Range: -0.2592

Max Act: 0.2487. Min Act: -0.0000

Data Index: 521872 (C4 (Web Text))

Max Activating Token Index: 571

Text #4

Max Range: 0.2592. Min Range: -0.2592

Max Act: 0.2369. Min Act: -0.0000

Data Index: 235983 (C4 (Web Text))

Max Activating Token Index: 28

Text #5

Max Range: 0.2592. Min Range: -0.2592

Max Act: 0.2424. Min Act: -0.0000

Data Index: 52993 (C4 (Web Text))

Max Activating Token Index: 213

Text #6

Max Range: 0.2592. Min Range: -0.2592

Max Act: 0.2344. Min Act: -0.0000

Data Index: 968701 (C4 (Web Text))

Max Activating Token Index: 106

Text #7

Max Range: 0.2592. Min Range: -0.2592

Max Act: 0.2479. Min Act: -0.0000

Data Index: 175457 (C4 (Web Text))

Max Activating Token Index: 103

Text #8

Max Range: 0.2592. Min Range: -0.2592

Max Act: 0.2260. Min Act: -0.0000

Data Index: 932504 (C4 (Web Text))

Max Activating Token Index: 937

Text #9

Max Range: 0.2592. Min Range: -0.2592

Max Act: 0.2194. Min Act: -0.0000

Data Index: 1259154 (C4 (Web Text))

Max Activating Token Index: 595

Text #10

Max Range: 0.2592. Min Range: -0.2592

Max Act: 0.2426. Min Act: -0.0000

Data Index: 1113041 (C4 (Web Text))

Max Activating Token Index: 970

Text #11

Max Range: 0.2592. Min Range: -0.2592

Max Act: 0.2279. Min Act: -0.0000

Data Index: 963056 (C4 (Web Text))

Max Activating Token Index: 31

Text #12

Max Range: 0.2592. Min Range: -0.2592

Max Act: 0.2337. Min Act: -0.0000

Data Index: 190357 (C4 (Web Text))

Max Activating Token Index: 204

Text #13

Max Range: 0.2592. Min Range: -0.2592

Max Act: 0.2233. Min Act: -0.0000

Data Index: 1311443 (C4 (Web Text))

Max Activating Token Index: 546

Text #14

Max Range: 0.2592. Min Range: -0.2592

Max Act: 0.2229. Min Act: -0.0000

Data Index: 2917 (C4 (Web Text))

Max Activating Token Index: 533

Text #15

Max Range: 0.2592. Min Range: -0.2592

Max Act: 0.2390. Min Act: -0.0000

Data Index: 1344864 (C4 (Web Text))

Max Activating Token Index: 367

Text #16

Max Range: 0.2592. Min Range: -0.2592

Max Act: 0.2161. Min Act: -0.0000

Data Index: 854177 (C4 (Web Text))

Max Activating Token Index: 595

Text #17

Max Range: 0.2592. Min Range: -0.2592

Max Act: 0.2299. Min Act: -0.0000

Data Index: 194589 (C4 (Web Text))

Max Activating Token Index: 524

Text #18

Max Range: 0.2592. Min Range: -0.2592

Max Act: 0.2219. Min Act: -0.0000

Data Index: 1168103 (C4 (Web Text))

Max Activating Token Index: 178

Text #19

Max Range: 0.2592. Min Range: -0.2592

Max Act: 0.2214. Min Act: -0.0000

Data Index: 1273098 (C4 (Web Text))

Max Activating Token Index: 134