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

Dataset: The Pile

Neuron 1738 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8289. Min Range: -3.8289

Max Act: 3.8289. Min Act: -0.0000

Data Index: 1672129 (The Pile)

Max Activating Token Index: 16

Text #1

Max Range: 3.8289. Min Range: -3.8289

Max Act: 3.8265. Min Act: -0.0000

Data Index: 395261 (The Pile)

Max Activating Token Index: 727

Text #2

Max Range: 3.8289. Min Range: -3.8289

Max Act: 3.6338. Min Act: -0.0000

Data Index: 1267404 (The Pile)

Max Activating Token Index: 63

Text #3

Max Range: 3.8289. Min Range: -3.8289

Max Act: 3.5968. Min Act: -0.0000

Data Index: 1915065 (The Pile)

Max Activating Token Index: 119

Text #4

Max Range: 3.8289. Min Range: -3.8289

Max Act: 3.7367. Min Act: -0.0000

Data Index: 547129 (The Pile)

Max Activating Token Index: 19

Text #5

Max Range: 3.8289. Min Range: -3.8289

Max Act: 3.5635. Min Act: -0.0000

Data Index: 416578 (The Pile)

Max Activating Token Index: 337

Text #6

Max Range: 3.8289. Min Range: -3.8289

Max Act: 3.5770. Min Act: -0.0000

Data Index: 1132458 (The Pile)

Max Activating Token Index: 33

Text #7

Max Range: 3.8289. Min Range: -3.8289

Max Act: 3.5189. Min Act: -0.0000

Data Index: 1083169 (The Pile)

Max Activating Token Index: 180

Text #8

Max Range: 3.8289. Min Range: -3.8289

Max Act: 3.5030. Min Act: -0.0000

Data Index: 1175103 (The Pile)

Max Activating Token Index: 201

Text #9

Max Range: 3.8289. Min Range: -3.8289

Max Act: 3.4781. Min Act: -0.0000

Data Index: 576204 (The Pile)

Max Activating Token Index: 44

Text #10

Max Range: 3.8289. Min Range: -3.8289

Max Act: 3.6447. Min Act: -0.0000

Data Index: 1666380 (The Pile)

Max Activating Token Index: 675

Text #11

Max Range: 3.8289. Min Range: -3.8289

Max Act: 3.5396. Min Act: -0.0000

Data Index: 821753 (The Pile)

Max Activating Token Index: 439

Text #12

Max Range: 3.8289. Min Range: -3.8289

Max Act: 3.5414. Min Act: -0.0000

Data Index: 50940 (The Pile)

Max Activating Token Index: 82

Text #13

Max Range: 3.8289. Min Range: -3.8289

Max Act: 3.2194. Min Act: -0.0000

Data Index: 1100683 (The Pile)

Max Activating Token Index: 177

Text #14

Max Range: 3.8289. Min Range: -3.8289

Max Act: 3.3176. Min Act: -0.0000

Data Index: 471579 (The Pile)

Max Activating Token Index: 320

Text #15

Max Range: 3.8289. Min Range: -3.8289

Max Act: 3.2923. Min Act: -0.0000

Data Index: 1079583 (The Pile)

Max Activating Token Index: 29

Text #16

Max Range: 3.8289. Min Range: -3.8289

Max Act: 3.0927. Min Act: -0.0000

Data Index: 510529 (The Pile)

Max Activating Token Index: 408

Text #17

Max Range: 3.8289. Min Range: -3.8289

Max Act: 2.9279. Min Act: -0.0000

Data Index: 1905000 (The Pile)

Max Activating Token Index: 703

Text #18

Max Range: 3.8289. Min Range: -3.8289

Max Act: 3.2127. Min Act: -0.0000

Data Index: 605077 (The Pile)

Max Activating Token Index: 253

Text #19

Max Range: 3.8289. Min Range: -3.8289

Max Act: 3.1989. Min Act: -0.0000

Data Index: 1201475 (The Pile)

Max Activating Token Index: 11