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

Dataset: The Pile

Neuron 4266 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: 0.6244. Min Range: -0.6244

Max Act: 0.6244. Min Act: -0.0000

Data Index: 141258 (The Pile)

Max Activating Token Index: 289

Text #1

Max Range: 0.6244. Min Range: -0.6244

Max Act: 0.5594. Min Act: -0.0000

Data Index: 826336 (The Pile)

Max Activating Token Index: 179

Text #2

Max Range: 0.6244. Min Range: -0.6244

Max Act: 0.5915. Min Act: -0.0000

Data Index: 1110887 (The Pile)

Max Activating Token Index: 245

Text #3

Max Range: 0.6244. Min Range: -0.6244

Max Act: 0.5539. Min Act: -0.0000

Data Index: 1238247 (The Pile)

Max Activating Token Index: 397

Text #4

Max Range: 0.6244. Min Range: -0.6244

Max Act: 0.5661. Min Act: -0.0000

Data Index: 242108 (The Pile)

Max Activating Token Index: 970

Text #5

Max Range: 0.6244. Min Range: -0.6244

Max Act: 0.5513. Min Act: -0.0000

Data Index: 1375592 (The Pile)

Max Activating Token Index: 996

Text #6

Max Range: 0.6244. Min Range: -0.6244

Max Act: 0.5374. Min Act: -0.0000

Data Index: 1593528 (The Pile)

Max Activating Token Index: 70

Text #7

Max Range: 0.6244. Min Range: -0.6244

Max Act: 0.5209. Min Act: -0.0000

Data Index: 417409 (The Pile)

Max Activating Token Index: 702

Text #8

Max Range: 0.6244. Min Range: -0.6244

Max Act: 0.5024. Min Act: -0.0000

Data Index: 173908 (The Pile)

Max Activating Token Index: 758

Text #9

Max Range: 0.6244. Min Range: -0.6244

Max Act: 0.4811. Min Act: -0.0000

Data Index: 1308116 (The Pile)

Max Activating Token Index: 277

Text #10

Max Range: 0.6244. Min Range: -0.6244

Max Act: 0.5178. Min Act: -0.0000

Data Index: 377671 (The Pile)

Max Activating Token Index: 751

Text #11

Max Range: 0.6244. Min Range: -0.6244

Max Act: 0.4976. Min Act: -0.0000

Data Index: 1591130 (The Pile)

Max Activating Token Index: 103

Text #12

Max Range: 0.6244. Min Range: -0.6244

Max Act: 0.4936. Min Act: -0.0000

Data Index: 1375535 (The Pile)

Max Activating Token Index: 151

Text #13

Max Range: 0.6244. Min Range: -0.6244

Max Act: 0.4680. Min Act: -0.0000

Data Index: 372366 (The Pile)

Max Activating Token Index: 200

Text #14

Max Range: 0.6244. Min Range: -0.6244

Max Act: 0.4869. Min Act: -0.0000

Data Index: 1467181 (The Pile)

Max Activating Token Index: 482

Text #15

Max Range: 0.6244. Min Range: -0.6244

Max Act: 0.4737. Min Act: -0.0000

Data Index: 1803053 (The Pile)

Max Activating Token Index: 431

Text #16

Max Range: 0.6244. Min Range: -0.6244

Max Act: 0.4651. Min Act: -0.0000

Data Index: 1122204 (The Pile)

Max Activating Token Index: 66

Text #17

Max Range: 0.6244. Min Range: -0.6244

Max Act: 0.4586. Min Act: -0.0000

Data Index: 834581 (The Pile)

Max Activating Token Index: 916

Text #18

Max Range: 0.6244. Min Range: -0.6244

Max Act: 0.4532. Min Act: -0.0000

Data Index: 1443364 (The Pile)

Max Activating Token Index: 356

Text #19

Max Range: 0.6244. Min Range: -0.6244

Max Act: 0.4677. Min Act: -0.0000

Data Index: 373569 (The Pile)

Max Activating Token Index: 9