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

Dataset: The Pile

Neuron 4073 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7854. Min Range: -0.7854

Max Act: 0.7777. Min Act: -0.0000

Data Index: 1024311 (The Pile)

Max Activating Token Index: 16

Text #1

Max Range: 0.7854. Min Range: -0.7854

Max Act: 0.7462. Min Act: -0.0000

Data Index: 1560237 (The Pile)

Max Activating Token Index: 662

Text #2

Max Range: 0.7854. Min Range: -0.7854

Max Act: 0.7633. Min Act: -0.0000

Data Index: 66814 (The Pile)

Max Activating Token Index: 135

Text #3

Max Range: 0.7854. Min Range: -0.7854

Max Act: 0.7196. Min Act: -0.0000

Data Index: 184739 (The Pile)

Max Activating Token Index: 948

Text #4

Max Range: 0.7854. Min Range: -0.7854

Max Act: 0.7854. Min Act: -0.0000

Data Index: 1957146 (The Pile)

Max Activating Token Index: 943

Text #5

Max Range: 0.7854. Min Range: -0.7854

Max Act: 0.6731. Min Act: -0.0000

Data Index: 82303 (The Pile)

Max Activating Token Index: 526

Text #6

Max Range: 0.7854. Min Range: -0.7854

Max Act: 0.6595. Min Act: -0.0000

Data Index: 737631 (The Pile)

Max Activating Token Index: 758

Text #7

Max Range: 0.7854. Min Range: -0.7854

Max Act: 0.7364. Min Act: -0.0000

Data Index: 1932308 (The Pile)

Max Activating Token Index: 213

Text #8

Max Range: 0.7854. Min Range: -0.7854

Max Act: 0.7259. Min Act: -0.0000

Data Index: 485818 (The Pile)

Max Activating Token Index: 884

Text #9

Max Range: 0.7854. Min Range: -0.7854

Max Act: 0.7093. Min Act: -0.0000

Data Index: 905115 (The Pile)

Max Activating Token Index: 541

Text #10

Max Range: 0.7854. Min Range: -0.7854

Max Act: 0.6202. Min Act: -0.0000

Data Index: 966608 (The Pile)

Max Activating Token Index: 336

Text #11

Max Range: 0.7854. Min Range: -0.7854

Max Act: 0.6311. Min Act: -0.0000

Data Index: 46581 (The Pile)

Max Activating Token Index: 693

Text #12

Max Range: 0.7854. Min Range: -0.7854

Max Act: 0.5737. Min Act: -0.0000

Data Index: 60363 (The Pile)

Max Activating Token Index: 767

Text #13

Max Range: 0.7854. Min Range: -0.7854

Max Act: 0.6141. Min Act: -0.0000

Data Index: 650976 (The Pile)

Max Activating Token Index: 517

Text #14

Max Range: 0.7854. Min Range: -0.7854

Max Act: 0.6529. Min Act: -0.0000

Data Index: 199144 (The Pile)

Max Activating Token Index: 671

Text #15

Max Range: 0.7854. Min Range: -0.7854

Max Act: 0.6138. Min Act: -0.0000

Data Index: 1622812 (The Pile)

Max Activating Token Index: 376

Text #16

Max Range: 0.7854. Min Range: -0.7854

Max Act: 0.5631. Min Act: -0.0000

Data Index: 1983171 (The Pile)

Max Activating Token Index: 220

Text #17

Max Range: 0.7854. Min Range: -0.7854

Max Act: 0.5444. Min Act: -0.0000

Data Index: 1929283 (The Pile)

Max Activating Token Index: 403

Text #18

Max Range: 0.7854. Min Range: -0.7854

Max Act: 0.5326. Min Act: -0.0000

Data Index: 546406 (The Pile)

Max Activating Token Index: 355

Text #19

Max Range: 0.7854. Min Range: -0.7854

Max Act: 0.5904. Min Act: -0.0000

Data Index: 1432396 (The Pile)

Max Activating Token Index: 355