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

Dataset: The Pile

Neuron 3134 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: 1.8406. Min Range: -1.8406

Max Act: 1.8406. Min Act: -0.0000

Data Index: 1919804 (The Pile)

Max Activating Token Index: 682

Text #1

Max Range: 1.8406. Min Range: -1.8406

Max Act: 1.7535. Min Act: -0.0000

Data Index: 1025304 (The Pile)

Max Activating Token Index: 979

Text #2

Max Range: 1.8406. Min Range: -1.8406

Max Act: 1.6951. Min Act: -0.0000

Data Index: 1101185 (The Pile)

Max Activating Token Index: 164

Text #3

Max Range: 1.8406. Min Range: -1.8406

Max Act: 1.5088. Min Act: -0.0000

Data Index: 841886 (The Pile)

Max Activating Token Index: 678

Text #4

Max Range: 1.8406. Min Range: -1.8406

Max Act: 1.5559. Min Act: -0.0000

Data Index: 1975548 (The Pile)

Max Activating Token Index: 531

Text #5

Max Range: 1.8406. Min Range: -1.8406

Max Act: 1.6340. Min Act: -0.0000

Data Index: 1583131 (The Pile)

Max Activating Token Index: 733

Text #6

Max Range: 1.8406. Min Range: -1.8406

Max Act: 1.5345. Min Act: -0.0000

Data Index: 1186817 (The Pile)

Max Activating Token Index: 140

Text #7

Max Range: 1.8406. Min Range: -1.8406

Max Act: 1.5360. Min Act: -0.0000

Data Index: 83813 (The Pile)

Max Activating Token Index: 572

Text #8

Max Range: 1.8406. Min Range: -1.8406

Max Act: 1.7741. Min Act: -0.0000

Data Index: 1994425 (The Pile)

Max Activating Token Index: 962

Text #9

Max Range: 1.8406. Min Range: -1.8406

Max Act: 1.4610. Min Act: -0.0000

Data Index: 929920 (The Pile)

Max Activating Token Index: 154

Text #10

Max Range: 1.8406. Min Range: -1.8406

Max Act: 1.5245. Min Act: -0.0000

Data Index: 1993351 (The Pile)

Max Activating Token Index: 489

Text #11

Max Range: 1.8406. Min Range: -1.8406

Max Act: 1.5259. Min Act: -0.0000

Data Index: 716431 (The Pile)

Max Activating Token Index: 816

Text #12

Max Range: 1.8406. Min Range: -1.8406

Max Act: 1.5092. Min Act: -0.0000

Data Index: 307663 (The Pile)

Max Activating Token Index: 938

Text #13

Max Range: 1.8406. Min Range: -1.8406

Max Act: 1.5176. Min Act: -0.0000

Data Index: 44360 (The Pile)

Max Activating Token Index: 386

Text #14

Max Range: 1.8406. Min Range: -1.8406

Max Act: 1.5061. Min Act: -0.0000

Data Index: 1754896 (The Pile)

Max Activating Token Index: 606

Text #15

Max Range: 1.8406. Min Range: -1.8406

Max Act: 1.4033. Min Act: -0.0000

Data Index: 1848584 (The Pile)

Max Activating Token Index: 308

Text #16

Max Range: 1.8406. Min Range: -1.8406

Max Act: 1.3935. Min Act: -0.0000

Data Index: 408912 (The Pile)

Max Activating Token Index: 739

Text #17

Max Range: 1.8406. Min Range: -1.8406

Max Act: 1.3962. Min Act: -0.0000

Data Index: 32384 (The Pile)

Max Activating Token Index: 359

Text #18

Max Range: 1.8406. Min Range: -1.8406

Max Act: 1.4577. Min Act: -0.0000

Data Index: 1055525 (The Pile)

Max Activating Token Index: 1023

Text #19

Max Range: 1.8406. Min Range: -1.8406

Max Act: 1.5374. Min Act: -0.0000

Data Index: 278224 (The Pile)

Max Activating Token Index: 779