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

Dataset: The Pile

Neuron 4169 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3637. Min Range: -0.3637

Max Act: 0.3637. Min Act: -0.0000

Data Index: 1880450 (The Pile)

Max Activating Token Index: 116

Text #1

Max Range: 0.3637. Min Range: -0.3637

Max Act: 0.3533. Min Act: -0.0000

Data Index: 1049790 (The Pile)

Max Activating Token Index: 153

Text #2

Max Range: 0.3637. Min Range: -0.3637

Max Act: 0.2990. Min Act: -0.0000

Data Index: 1690761 (The Pile)

Max Activating Token Index: 82

Text #3

Max Range: 0.3637. Min Range: -0.3637

Max Act: 0.2859. Min Act: -0.0000

Data Index: 371703 (The Pile)

Max Activating Token Index: 651

Text #4

Max Range: 0.3637. Min Range: -0.3637

Max Act: 0.2401. Min Act: -0.0000

Data Index: 488773 (The Pile)

Max Activating Token Index: 306

Text #5

Max Range: 0.3637. Min Range: -0.3637

Max Act: 0.2775. Min Act: -0.0000

Data Index: 592078 (The Pile)

Max Activating Token Index: 123

Text #6

Max Range: 0.3637. Min Range: -0.3637

Max Act: 0.2072. Min Act: -0.0000

Data Index: 304350 (The Pile)

Max Activating Token Index: 819

Text #7

Max Range: 0.3637. Min Range: -0.3637

Max Act: 0.2199. Min Act: -0.0000

Data Index: 1947928 (The Pile)

Max Activating Token Index: 103

Text #8

Max Range: 0.3637. Min Range: -0.3637

Max Act: 0.1859. Min Act: -0.0000

Data Index: 308186 (The Pile)

Max Activating Token Index: 272

Text #9

Max Range: 0.3637. Min Range: -0.3637

Max Act: 0.1902. Min Act: -0.0000

Data Index: 225218 (The Pile)

Max Activating Token Index: 313

Text #10

Max Range: 0.3637. Min Range: -0.3637

Max Act: 0.1791. Min Act: -0.0000

Data Index: 1356143 (The Pile)

Max Activating Token Index: 982

Text #11

Max Range: 0.3637. Min Range: -0.3637

Max Act: 0.1594. Min Act: -0.0000

Data Index: 691611 (The Pile)

Max Activating Token Index: 405

Text #12

Max Range: 0.3637. Min Range: -0.3637

Max Act: 0.1406. Min Act: -0.0000

Data Index: 861004 (The Pile)

Max Activating Token Index: 127

Text #13

Max Range: 0.3637. Min Range: -0.3637

Max Act: 0.1333. Min Act: -0.0000

Data Index: 1806182 (The Pile)

Max Activating Token Index: 426

Text #14

Max Range: 0.3637. Min Range: -0.3637

Max Act: 0.1433. Min Act: -0.0000

Data Index: 1011561 (The Pile)

Max Activating Token Index: 599

Text #15

Max Range: 0.3637. Min Range: -0.3637

Max Act: 0.1267. Min Act: -0.0000

Data Index: 1403820 (The Pile)

Max Activating Token Index: 935

Text #16

Max Range: 0.3637. Min Range: -0.3637

Max Act: 0.1363. Min Act: -0.0000

Data Index: 67585 (The Pile)

Max Activating Token Index: 395

Text #17

Max Range: 0.3637. Min Range: -0.3637

Max Act: 0.1214. Min Act: -0.0000

Data Index: 529944 (The Pile)

Max Activating Token Index: 169

Text #18

Max Range: 0.3637. Min Range: -0.3637

Max Act: 0.1311. Min Act: -0.0000

Data Index: 1191763 (The Pile)

Max Activating Token Index: 305

Text #19

Max Range: 0.3637. Min Range: -0.3637

Max Act: 0.1316. Min Act: -0.0000

Data Index: 1120018 (The Pile)

Max Activating Token Index: 684