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

Dataset: The Pile

Neuron 4966 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3623. Min Range: -0.3623

Max Act: 0.3623. Min Act: -0.0000

Data Index: 1504670 (The Pile)

Max Activating Token Index: 392

Text #1

Max Range: 0.3623. Min Range: -0.3623

Max Act: 0.3286. Min Act: -0.0000

Data Index: 441542 (The Pile)

Max Activating Token Index: 426

Text #2

Max Range: 0.3623. Min Range: -0.3623

Max Act: 0.2838. Min Act: -0.0000

Data Index: 1148002 (The Pile)

Max Activating Token Index: 745

Text #3

Max Range: 0.3623. Min Range: -0.3623

Max Act: 0.2891. Min Act: -0.0000

Data Index: 1626013 (The Pile)

Max Activating Token Index: 407

Text #4

Max Range: 0.3623. Min Range: -0.3623

Max Act: 0.2842. Min Act: -0.0000

Data Index: 1872572 (The Pile)

Max Activating Token Index: 204

Text #5

Max Range: 0.3623. Min Range: -0.3623

Max Act: 0.2388. Min Act: -0.0000

Data Index: 903206 (The Pile)

Max Activating Token Index: 993

Text #6

Max Range: 0.3623. Min Range: -0.3623

Max Act: 0.2337. Min Act: -0.0000

Data Index: 910362 (The Pile)

Max Activating Token Index: 252

Text #7

Max Range: 0.3623. Min Range: -0.3623

Max Act: 0.2459. Min Act: -0.0000

Data Index: 1108678 (The Pile)

Max Activating Token Index: 492

Text #8

Max Range: 0.3623. Min Range: -0.3623

Max Act: 0.2061. Min Act: -0.0000

Data Index: 1680159 (The Pile)

Max Activating Token Index: 229

Text #9

Max Range: 0.3623. Min Range: -0.3623

Max Act: 0.2223. Min Act: -0.0000

Data Index: 884862 (The Pile)

Max Activating Token Index: 415

Text #10

Max Range: 0.3623. Min Range: -0.3623

Max Act: 0.2578. Min Act: -0.0000

Data Index: 1992976 (The Pile)

Max Activating Token Index: 346

Text #11

Max Range: 0.3623. Min Range: -0.3623

Max Act: 0.2343. Min Act: -0.0000

Data Index: 1496705 (The Pile)

Max Activating Token Index: 189

Text #12

Max Range: 0.3623. Min Range: -0.3623

Max Act: 0.2260. Min Act: -0.0000

Data Index: 1410202 (The Pile)

Max Activating Token Index: 46

Text #13

Max Range: 0.3623. Min Range: -0.3623

Max Act: 0.1913. Min Act: -0.0000

Data Index: 664362 (The Pile)

Max Activating Token Index: 867

Text #14

Max Range: 0.3623. Min Range: -0.3623

Max Act: 0.1907. Min Act: -0.0000

Data Index: 1972347 (The Pile)

Max Activating Token Index: 113

Text #15

Max Range: 0.3623. Min Range: -0.3623

Max Act: 0.1969. Min Act: -0.0000

Data Index: 1616647 (The Pile)

Max Activating Token Index: 95

Text #16

Max Range: 0.3623. Min Range: -0.3623

Max Act: 0.1869. Min Act: -0.0000

Data Index: 1138882 (The Pile)

Max Activating Token Index: 238

Text #17

Max Range: 0.3623. Min Range: -0.3623

Max Act: 0.1918. Min Act: -0.0000

Data Index: 691942 (The Pile)

Max Activating Token Index: 567

Text #18

Max Range: 0.3623. Min Range: -0.3623

Max Act: 0.1876. Min Act: -0.0000

Data Index: 502538 (The Pile)

Max Activating Token Index: 142

Text #19

Max Range: 0.3623. Min Range: -0.3623

Max Act: 0.1807. Min Act: -0.0000

Data Index: 340728 (The Pile)

Max Activating Token Index: 639