Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1967 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0218. Min Act: -0.0006

Data Index: 1433805 (Python Code)

Max Activating Token Index: 580

Text #1

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0193. Min Act: -0.0006

Data Index: 1304026 (C4 (Web Text))

Max Activating Token Index: 540

Text #2

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0194. Min Act: -0.0006

Data Index: 1642728 (Python Code)

Max Activating Token Index: 727

Text #3

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0193. Min Act: -0.0005

Data Index: 1631544 (Python Code)

Max Activating Token Index: 739

Text #4

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0186. Min Act: -0.0006

Data Index: 552892 (C4 (Web Text))

Max Activating Token Index: 250

Text #5

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0185. Min Act: -0.0006

Data Index: 1467890 (Python Code)

Max Activating Token Index: 803

Text #6

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0188. Min Act: -0.0006

Data Index: 1404226 (Python Code)

Max Activating Token Index: 575

Text #7

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0187. Min Act: -0.0006

Data Index: 1618388 (Python Code)

Max Activating Token Index: 28

Text #8

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0186. Min Act: -0.0006

Data Index: 1551826 (Python Code)

Max Activating Token Index: 174

Text #9

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0183. Min Act: -0.0005

Data Index: 1304172 (C4 (Web Text))

Max Activating Token Index: 719

Text #10

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0179. Min Act: -0.0006

Data Index: 1655155 (Python Code)

Max Activating Token Index: 179

Text #11

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0182. Min Act: -0.0006

Data Index: 1367115 (Python Code)

Max Activating Token Index: 297

Text #12

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0181. Min Act: -0.0006

Data Index: 1630363 (Python Code)

Max Activating Token Index: 630

Text #13

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0180. Min Act: -0.0006

Data Index: 1611392 (Python Code)

Max Activating Token Index: 176

Text #14

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0179. Min Act: -0.0006

Data Index: 1605094 (Python Code)

Max Activating Token Index: 620

Text #15

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0174. Min Act: -0.0006

Data Index: 1523242 (Python Code)

Max Activating Token Index: 919

Text #16

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0173. Min Act: -0.0006

Data Index: 952843 (C4 (Web Text))

Max Activating Token Index: 838

Text #17

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0172. Min Act: -0.0006

Data Index: 717692 (C4 (Web Text))

Max Activating Token Index: 766

Text #18

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0176. Min Act: -0.0005

Data Index: 1613252 (Python Code)

Max Activating Token Index: 376

Text #19

Max Range: 0.0218. Min Range: -0.0218

Max Act: 0.0175. Min Act: -0.0006

Data Index: 1604594 (Python Code)

Max Activating Token Index: 636