Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4258 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.5207. Min Range: -1.5207

Max Act: 1.5207. Min Act: -0.0000

Data Index: 1264117 (C4 (Web Text))

Max Activating Token Index: 431

Text #1

Max Range: 1.5207. Min Range: -1.5207

Max Act: 1.4725. Min Act: -0.0000

Data Index: 541082 (C4 (Web Text))

Max Activating Token Index: 528

Text #2

Max Range: 1.5207. Min Range: -1.5207

Max Act: 1.4652. Min Act: -0.0000

Data Index: 1486429 (Python Code)

Max Activating Token Index: 130

Text #3

Max Range: 1.5207. Min Range: -1.5207

Max Act: 1.5008. Min Act: -0.0000

Data Index: 617699 (C4 (Web Text))

Max Activating Token Index: 152

Text #4

Max Range: 1.5207. Min Range: -1.5207

Max Act: 1.4092. Min Act: -0.0000

Data Index: 624804 (C4 (Web Text))

Max Activating Token Index: 29

Text #5

Max Range: 1.5207. Min Range: -1.5207

Max Act: 1.3066. Min Act: -0.0000

Data Index: 1383075 (Python Code)

Max Activating Token Index: 998

Text #6

Max Range: 1.5207. Min Range: -1.5207

Max Act: 1.3055. Min Act: -0.0000

Data Index: 764800 (C4 (Web Text))

Max Activating Token Index: 142

Text #7

Max Range: 1.5207. Min Range: -1.5207

Max Act: 1.3104. Min Act: -0.0000

Data Index: 472702 (C4 (Web Text))

Max Activating Token Index: 666

Text #8

Max Range: 1.5207. Min Range: -1.5207

Max Act: 1.3282. Min Act: -0.0000

Data Index: 1653060 (Python Code)

Max Activating Token Index: 799

Text #9

Max Range: 1.5207. Min Range: -1.5207

Max Act: 1.2982. Min Act: -0.0000

Data Index: 154147 (C4 (Web Text))

Max Activating Token Index: 334

Text #10

Max Range: 1.5207. Min Range: -1.5207

Max Act: 1.3471. Min Act: -0.0000

Data Index: 1498391 (Python Code)

Max Activating Token Index: 810

Text #11

Max Range: 1.5207. Min Range: -1.5207

Max Act: 1.2326. Min Act: -0.0000

Data Index: 1236090 (C4 (Web Text))

Max Activating Token Index: 138

Text #12

Max Range: 1.5207. Min Range: -1.5207

Max Act: 1.1121. Min Act: -0.0000

Data Index: 805117 (C4 (Web Text))

Max Activating Token Index: 1019

Text #13

Max Range: 1.5207. Min Range: -1.5207

Max Act: 1.1191. Min Act: -0.0000

Data Index: 1518293 (Python Code)

Max Activating Token Index: 124

Text #14

Max Range: 1.5207. Min Range: -1.5207

Max Act: 1.1542. Min Act: -0.0000

Data Index: 1431791 (Python Code)

Max Activating Token Index: 637

Text #15

Max Range: 1.5207. Min Range: -1.5207

Max Act: 1.1536. Min Act: -0.0000

Data Index: 1612216 (Python Code)

Max Activating Token Index: 132

Text #16

Max Range: 1.5207. Min Range: -1.5207

Max Act: 1.1884. Min Act: -0.0000

Data Index: 376329 (C4 (Web Text))

Max Activating Token Index: 702

Text #17

Max Range: 1.5207. Min Range: -1.5207

Max Act: 1.1831. Min Act: -0.0000

Data Index: 272883 (C4 (Web Text))

Max Activating Token Index: 417

Text #18

Max Range: 1.5207. Min Range: -1.5207

Max Act: 1.1194. Min Act: -0.0000

Data Index: 25657 (C4 (Web Text))

Max Activating Token Index: 1012

Text #19

Max Range: 1.5207. Min Range: -1.5207

Max Act: 1.1788. Min Act: -0.0000

Data Index: 265850 (C4 (Web Text))

Max Activating Token Index: 84