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

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

Neuron 3643 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: 0.0435. Min Range: -0.0435

Max Act: 0.0435. Min Act: -0.0003

Data Index: 629636 (C4 (Web Text))

Max Activating Token Index: 111

Text #1

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0381. Min Act: -0.0003

Data Index: 1206141 (C4 (Web Text))

Max Activating Token Index: 740

Text #2

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0352. Min Act: -0.0003

Data Index: 1114855 (C4 (Web Text))

Max Activating Token Index: 171

Text #3

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0324. Min Act: -0.0003

Data Index: 495504 (C4 (Web Text))

Max Activating Token Index: 677

Text #4

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0315. Min Act: -0.0003

Data Index: 972542 (C4 (Web Text))

Max Activating Token Index: 551

Text #5

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0318. Min Act: -0.0002

Data Index: 1220304 (C4 (Web Text))

Max Activating Token Index: 261

Text #6

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0310. Min Act: -0.0003

Data Index: 94899 (C4 (Web Text))

Max Activating Token Index: 903

Text #7

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0308. Min Act: -0.0003

Data Index: 1395029 (Python Code)

Max Activating Token Index: 118

Text #8

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0307. Min Act: -0.0003

Data Index: 1504374 (Python Code)

Max Activating Token Index: 108

Text #9

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0307. Min Act: -0.0003

Data Index: 433165 (C4 (Web Text))

Max Activating Token Index: 87

Text #10

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0283. Min Act: -0.0003

Data Index: 526344 (C4 (Web Text))

Max Activating Token Index: 151

Text #11

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0301. Min Act: -0.0003

Data Index: 1102152 (C4 (Web Text))

Max Activating Token Index: 129

Text #12

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0310. Min Act: -0.0003

Data Index: 925593 (C4 (Web Text))

Max Activating Token Index: 732

Text #13

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0306. Min Act: -0.0003

Data Index: 462371 (C4 (Web Text))

Max Activating Token Index: 179

Text #14

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0299. Min Act: -0.0003

Data Index: 1539158 (Python Code)

Max Activating Token Index: 91

Text #15

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0301. Min Act: -0.0003

Data Index: 1458167 (Python Code)

Max Activating Token Index: 208

Text #16

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0291. Min Act: -0.0002

Data Index: 1214512 (C4 (Web Text))

Max Activating Token Index: 871

Text #17

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0284. Min Act: -0.0002

Data Index: 1613288 (Python Code)

Max Activating Token Index: 99

Text #18

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0286. Min Act: -0.0003

Data Index: 780043 (C4 (Web Text))

Max Activating Token Index: 148

Text #19

Max Range: 0.0435. Min Range: -0.0435

Max Act: 0.0292. Min Act: -0.0003

Data Index: 447266 (C4 (Web Text))

Max Activating Token Index: 629