Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3833 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0527. Min Act: -0.0003

Data Index: 828425 (C4 (Web Text))

Max Activating Token Index: 12

Text #1

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0354. Min Act: -0.0003

Data Index: 1078179 (C4 (Web Text))

Max Activating Token Index: 871

Text #2

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0336. Min Act: -0.0003

Data Index: 734280 (C4 (Web Text))

Max Activating Token Index: 52

Text #3

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0333. Min Act: -0.0003

Data Index: 1134351 (C4 (Web Text))

Max Activating Token Index: 379

Text #4

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0328. Min Act: -0.0003

Data Index: 927387 (C4 (Web Text))

Max Activating Token Index: 53

Text #5

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0325. Min Act: -0.0003

Data Index: 130427 (C4 (Web Text))

Max Activating Token Index: 106

Text #6

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0312. Min Act: -0.0003

Data Index: 935785 (C4 (Web Text))

Max Activating Token Index: 133

Text #7

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0295. Min Act: -0.0003

Data Index: 526111 (C4 (Web Text))

Max Activating Token Index: 142

Text #8

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0289. Min Act: -0.0003

Data Index: 930379 (C4 (Web Text))

Max Activating Token Index: 12

Text #9

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0284. Min Act: -0.0003

Data Index: 216988 (C4 (Web Text))

Max Activating Token Index: 23

Text #10

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0267. Min Act: -0.0003

Data Index: 1019058 (C4 (Web Text))

Max Activating Token Index: 129

Text #11

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0267. Min Act: -0.0003

Data Index: 555425 (C4 (Web Text))

Max Activating Token Index: 53

Text #12

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0278. Min Act: -0.0003

Data Index: 571859 (C4 (Web Text))

Max Activating Token Index: 158

Text #13

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0289. Min Act: -0.0003

Data Index: 777068 (C4 (Web Text))

Max Activating Token Index: 208

Text #14

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0265. Min Act: -0.0002

Data Index: 578588 (C4 (Web Text))

Max Activating Token Index: 277

Text #15

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0276. Min Act: -0.0003

Data Index: 1129120 (C4 (Web Text))

Max Activating Token Index: 26

Text #16

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0274. Min Act: -0.0003

Data Index: 84025 (C4 (Web Text))

Max Activating Token Index: 14

Text #17

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0284. Min Act: -0.0003

Data Index: 593401 (C4 (Web Text))

Max Activating Token Index: 76

Text #18

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0272. Min Act: -0.0003

Data Index: 1194004 (C4 (Web Text))

Max Activating Token Index: 31

Text #19

Max Range: 0.0527. Min Range: -0.0527

Max Act: 0.0272. Min Act: -0.0003

Data Index: 1328640 (C4 (Web Text))

Max Activating Token Index: 289