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

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

Neuron 4659 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: 2.7259. Min Range: -2.7259

Max Act: 2.7151. Min Act: -0.0000

Data Index: 923321 (C4 (Web Text))

Max Activating Token Index: 818

Text #1

Max Range: 2.7259. Min Range: -2.7259

Max Act: 2.6184. Min Act: -0.0000

Data Index: 554257 (C4 (Web Text))

Max Activating Token Index: 594

Text #2

Max Range: 2.7259. Min Range: -2.7259

Max Act: 2.7020. Min Act: -0.0000

Data Index: 580777 (C4 (Web Text))

Max Activating Token Index: 770

Text #3

Max Range: 2.7259. Min Range: -2.7259

Max Act: 2.7259. Min Act: -0.0000

Data Index: 235847 (C4 (Web Text))

Max Activating Token Index: 941

Text #4

Max Range: 2.7259. Min Range: -2.7259

Max Act: 2.6069. Min Act: -0.0000

Data Index: 1621947 (Python Code)

Max Activating Token Index: 348

Text #5

Max Range: 2.7259. Min Range: -2.7259

Max Act: 2.4742. Min Act: -0.0000

Data Index: 46056 (C4 (Web Text))

Max Activating Token Index: 616

Text #6

Max Range: 2.7259. Min Range: -2.7259

Max Act: 2.4059. Min Act: -0.0000

Data Index: 1565563 (Python Code)

Max Activating Token Index: 963

Text #7

Max Range: 2.7259. Min Range: -2.7259

Max Act: 2.2296. Min Act: -0.0000

Data Index: 283446 (C4 (Web Text))

Max Activating Token Index: 175

Text #8

Max Range: 2.7259. Min Range: -2.7259

Max Act: 2.3437. Min Act: -0.0000

Data Index: 672703 (C4 (Web Text))

Max Activating Token Index: 776

Text #9

Max Range: 2.7259. Min Range: -2.7259

Max Act: 2.3349. Min Act: -0.0000

Data Index: 372865 (C4 (Web Text))

Max Activating Token Index: 884

Text #10

Max Range: 2.7259. Min Range: -2.7259

Max Act: 2.1740. Min Act: -0.0000

Data Index: 5110 (C4 (Web Text))

Max Activating Token Index: 988

Text #11

Max Range: 2.7259. Min Range: -2.7259

Max Act: 2.2195. Min Act: -0.0000

Data Index: 394285 (C4 (Web Text))

Max Activating Token Index: 173

Text #12

Max Range: 2.7259. Min Range: -2.7259

Max Act: 2.1920. Min Act: -0.0000

Data Index: 284947 (C4 (Web Text))

Max Activating Token Index: 595

Text #13

Max Range: 2.7259. Min Range: -2.7259

Max Act: 2.1759. Min Act: -0.0000

Data Index: 833878 (C4 (Web Text))

Max Activating Token Index: 117

Text #14

Max Range: 2.7259. Min Range: -2.7259

Max Act: 2.1850. Min Act: -0.0000

Data Index: 666453 (C4 (Web Text))

Max Activating Token Index: 635

Text #15

Max Range: 2.7259. Min Range: -2.7259

Max Act: 2.1395. Min Act: -0.0000

Data Index: 210081 (C4 (Web Text))

Max Activating Token Index: 443

Text #16

Max Range: 2.7259. Min Range: -2.7259

Max Act: 2.1282. Min Act: -0.0000

Data Index: 1238189 (C4 (Web Text))

Max Activating Token Index: 133

Text #17

Max Range: 2.7259. Min Range: -2.7259

Max Act: 2.1188. Min Act: -0.0000

Data Index: 28665 (C4 (Web Text))

Max Activating Token Index: 158

Text #18

Max Range: 2.7259. Min Range: -2.7259

Max Act: 2.1012. Min Act: -0.0000

Data Index: 1405976 (Python Code)

Max Activating Token Index: 875

Text #19

Max Range: 2.7259. Min Range: -2.7259

Max Act: 2.1938. Min Act: -0.0000

Data Index: 107973 (C4 (Web Text))

Max Activating Token Index: 686