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

Dataset: The Pile

Neuron 3661 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: 1.8884. Min Range: -1.8884

Max Act: 1.8307. Min Act: -0.0000

Data Index: 1726483 (The Pile)

Max Activating Token Index: 705

Text #1

Max Range: 1.8884. Min Range: -1.8884

Max Act: 1.8884. Min Act: -0.0000

Data Index: 1185364 (The Pile)

Max Activating Token Index: 105

Text #2

Max Range: 1.8884. Min Range: -1.8884

Max Act: 1.7667. Min Act: -0.0000

Data Index: 608446 (The Pile)

Max Activating Token Index: 188

Text #3

Max Range: 1.8884. Min Range: -1.8884

Max Act: 1.6107. Min Act: -0.0000

Data Index: 362839 (The Pile)

Max Activating Token Index: 75

Text #4

Max Range: 1.8884. Min Range: -1.8884

Max Act: 1.7869. Min Act: -0.0000

Data Index: 336161 (The Pile)

Max Activating Token Index: 528

Text #5

Max Range: 1.8884. Min Range: -1.8884

Max Act: 1.6047. Min Act: -0.0000

Data Index: 225304 (The Pile)

Max Activating Token Index: 135

Text #6

Max Range: 1.8884. Min Range: -1.8884

Max Act: 1.6299. Min Act: -0.0000

Data Index: 1725159 (The Pile)

Max Activating Token Index: 38

Text #7

Max Range: 1.8884. Min Range: -1.8884

Max Act: 1.6077. Min Act: -0.0000

Data Index: 542197 (The Pile)

Max Activating Token Index: 295

Text #8

Max Range: 1.8884. Min Range: -1.8884

Max Act: 1.5977. Min Act: -0.0000

Data Index: 1728712 (The Pile)

Max Activating Token Index: 242

Text #9

Max Range: 1.8884. Min Range: -1.8884

Max Act: 1.5102. Min Act: -0.0000

Data Index: 1643329 (The Pile)

Max Activating Token Index: 528

Text #10

Max Range: 1.8884. Min Range: -1.8884

Max Act: 1.5950. Min Act: -0.0000

Data Index: 1983703 (The Pile)

Max Activating Token Index: 391

Text #11

Max Range: 1.8884. Min Range: -1.8884

Max Act: 1.5725. Min Act: -0.0000

Data Index: 425563 (The Pile)

Max Activating Token Index: 786

Text #12

Max Range: 1.8884. Min Range: -1.8884

Max Act: 1.5510. Min Act: -0.0000

Data Index: 1345783 (The Pile)

Max Activating Token Index: 108

Text #13

Max Range: 1.8884. Min Range: -1.8884

Max Act: 1.4586. Min Act: -0.0000

Data Index: 682031 (The Pile)

Max Activating Token Index: 375

Text #14

Max Range: 1.8884. Min Range: -1.8884

Max Act: 1.4444. Min Act: -0.0000

Data Index: 278710 (The Pile)

Max Activating Token Index: 254

Text #15

Max Range: 1.8884. Min Range: -1.8884

Max Act: 1.5168. Min Act: -0.0000

Data Index: 1546481 (The Pile)

Max Activating Token Index: 699

Text #16

Max Range: 1.8884. Min Range: -1.8884

Max Act: 1.3559. Min Act: -0.0000

Data Index: 301055 (The Pile)

Max Activating Token Index: 208

Text #17

Max Range: 1.8884. Min Range: -1.8884

Max Act: 1.5931. Min Act: -0.0000

Data Index: 1462406 (The Pile)

Max Activating Token Index: 132

Text #18

Max Range: 1.8884. Min Range: -1.8884

Max Act: 1.4000. Min Act: -0.0000

Data Index: 760099 (The Pile)

Max Activating Token Index: 738

Text #19

Max Range: 1.8884. Min Range: -1.8884

Max Act: 1.4094. Min Act: -0.0000

Data Index: 39940 (The Pile)

Max Activating Token Index: 309