Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2715 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.7788. Min Range: -1.7788

Max Act: 1.7788. Min Act: -0.0000

Data Index: 918721 (The Pile)

Max Activating Token Index: 523

Text #1

Max Range: 1.7788. Min Range: -1.7788

Max Act: 1.4588. Min Act: -0.0000

Data Index: 1294594 (The Pile)

Max Activating Token Index: 143

Text #2

Max Range: 1.7788. Min Range: -1.7788

Max Act: 1.2247. Min Act: -0.0000

Data Index: 1224487 (The Pile)

Max Activating Token Index: 197

Text #3

Max Range: 1.7788. Min Range: -1.7788

Max Act: 1.4803. Min Act: -0.0000

Data Index: 1885383 (The Pile)

Max Activating Token Index: 150

Text #4

Max Range: 1.7788. Min Range: -1.7788

Max Act: 1.2005. Min Act: -0.0000

Data Index: 1917899 (The Pile)

Max Activating Token Index: 191

Text #5

Max Range: 1.7788. Min Range: -1.7788

Max Act: 1.3188. Min Act: -0.0000

Data Index: 1849001 (The Pile)

Max Activating Token Index: 403

Text #6

Max Range: 1.7788. Min Range: -1.7788

Max Act: 1.2159. Min Act: -0.0000

Data Index: 1232013 (The Pile)

Max Activating Token Index: 33

Text #7

Max Range: 1.7788. Min Range: -1.7788

Max Act: 1.2620. Min Act: -0.0000

Data Index: 1870449 (The Pile)

Max Activating Token Index: 41

Text #8

Max Range: 1.7788. Min Range: -1.7788

Max Act: 1.1450. Min Act: -0.0000

Data Index: 297328 (The Pile)

Max Activating Token Index: 665

Text #9

Max Range: 1.7788. Min Range: -1.7788

Max Act: 1.3548. Min Act: -0.0000

Data Index: 1539829 (The Pile)

Max Activating Token Index: 401

Text #10

Max Range: 1.7788. Min Range: -1.7788

Max Act: 1.0448. Min Act: -0.0000

Data Index: 26704 (The Pile)

Max Activating Token Index: 204

Text #11

Max Range: 1.7788. Min Range: -1.7788

Max Act: 1.1766. Min Act: -0.0000

Data Index: 512150 (The Pile)

Max Activating Token Index: 129

Text #12

Max Range: 1.7788. Min Range: -1.7788

Max Act: 1.1948. Min Act: -0.0000

Data Index: 1302774 (The Pile)

Max Activating Token Index: 219

Text #13

Max Range: 1.7788. Min Range: -1.7788

Max Act: 1.2117. Min Act: -0.0000

Data Index: 365665 (The Pile)

Max Activating Token Index: 748

Text #14

Max Range: 1.7788. Min Range: -1.7788

Max Act: 1.1019. Min Act: -0.0000

Data Index: 515939 (The Pile)

Max Activating Token Index: 966

Text #15

Max Range: 1.7788. Min Range: -1.7788

Max Act: 1.0845. Min Act: -0.0000

Data Index: 1980485 (The Pile)

Max Activating Token Index: 160

Text #16

Max Range: 1.7788. Min Range: -1.7788

Max Act: 1.2162. Min Act: -0.0000

Data Index: 967158 (The Pile)

Max Activating Token Index: 409

Text #17

Max Range: 1.7788. Min Range: -1.7788

Max Act: 1.1750. Min Act: -0.0000

Data Index: 222607 (The Pile)

Max Activating Token Index: 236

Text #18

Max Range: 1.7788. Min Range: -1.7788

Max Act: 1.1977. Min Act: -0.0000

Data Index: 281567 (The Pile)

Max Activating Token Index: 14

Text #19

Max Range: 1.7788. Min Range: -1.7788

Max Act: 1.1311. Min Act: -0.0000

Data Index: 1159452 (The Pile)

Max Activating Token Index: 790