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

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

Neuron 4659 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2303. Min Range: -0.2303

Max Act: 0.2237. Min Act: -0.0003

Data Index: 531943 (C4 (Web Text))

Max Activating Token Index: 412

Text #1

Max Range: 0.2303. Min Range: -0.2303

Max Act: 0.2303. Min Act: -0.0002

Data Index: 879398 (C4 (Web Text))

Max Activating Token Index: 158

Text #2

Max Range: 0.2303. Min Range: -0.2303

Max Act: 0.2255. Min Act: -0.0003

Data Index: 1318912 (C4 (Web Text))

Max Activating Token Index: 594

Text #3

Max Range: 0.2303. Min Range: -0.2303

Max Act: 0.2277. Min Act: -0.0002

Data Index: 288140 (C4 (Web Text))

Max Activating Token Index: 136

Text #4

Max Range: 0.2303. Min Range: -0.2303

Max Act: 0.2194. Min Act: -0.0003

Data Index: 229046 (C4 (Web Text))

Max Activating Token Index: 53

Text #5

Max Range: 0.2303. Min Range: -0.2303

Max Act: 0.2173. Min Act: -0.0003

Data Index: 673424 (C4 (Web Text))

Max Activating Token Index: 646

Text #6

Max Range: 0.2303. Min Range: -0.2303

Max Act: 0.2160. Min Act: -0.0003

Data Index: 321642 (C4 (Web Text))

Max Activating Token Index: 631

Text #7

Max Range: 0.2303. Min Range: -0.2303

Max Act: 0.2227. Min Act: -0.0003

Data Index: 1053459 (C4 (Web Text))

Max Activating Token Index: 58

Text #8

Max Range: 0.2303. Min Range: -0.2303

Max Act: 0.2160. Min Act: -0.0003

Data Index: 363861 (C4 (Web Text))

Max Activating Token Index: 562

Text #9

Max Range: 0.2303. Min Range: -0.2303

Max Act: 0.2127. Min Act: -0.0003

Data Index: 756088 (C4 (Web Text))

Max Activating Token Index: 751

Text #10

Max Range: 0.2303. Min Range: -0.2303

Max Act: 0.2127. Min Act: -0.0003

Data Index: 1340280 (C4 (Web Text))

Max Activating Token Index: 817

Text #11

Max Range: 0.2303. Min Range: -0.2303

Max Act: 0.2202. Min Act: -0.0003

Data Index: 759988 (C4 (Web Text))

Max Activating Token Index: 156

Text #12

Max Range: 0.2303. Min Range: -0.2303

Max Act: 0.2109. Min Act: -0.0002

Data Index: 656320 (C4 (Web Text))

Max Activating Token Index: 394

Text #13

Max Range: 0.2303. Min Range: -0.2303

Max Act: 0.2110. Min Act: -0.0003

Data Index: 1095363 (C4 (Web Text))

Max Activating Token Index: 363

Text #14

Max Range: 0.2303. Min Range: -0.2303

Max Act: 0.2098. Min Act: -0.0003

Data Index: 54035 (C4 (Web Text))

Max Activating Token Index: 286

Text #15

Max Range: 0.2303. Min Range: -0.2303

Max Act: 0.2016. Min Act: -0.0003

Data Index: 327349 (C4 (Web Text))

Max Activating Token Index: 295

Text #16

Max Range: 0.2303. Min Range: -0.2303

Max Act: 0.2088. Min Act: -0.0003

Data Index: 275372 (C4 (Web Text))

Max Activating Token Index: 532

Text #17

Max Range: 0.2303. Min Range: -0.2303

Max Act: 0.2083. Min Act: -0.0003

Data Index: 1335228 (C4 (Web Text))

Max Activating Token Index: 246

Text #18

Max Range: 0.2303. Min Range: -0.2303

Max Act: 0.2065. Min Act: -0.0002

Data Index: 1163362 (C4 (Web Text))

Max Activating Token Index: 676

Text #19

Max Range: 0.2303. Min Range: -0.2303

Max Act: 0.2057. Min Act: -0.0003

Data Index: 685340 (C4 (Web Text))

Max Activating Token Index: 556