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

Dataset: The Pile

Neuron 2925 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: 0.7540. Min Range: -0.7540

Max Act: 0.7540. Min Act: -0.0000

Data Index: 719800 (The Pile)

Max Activating Token Index: 389

Text #1

Max Range: 0.7540. Min Range: -0.7540

Max Act: 0.5607. Min Act: -0.0000

Data Index: 200877 (The Pile)

Max Activating Token Index: 505

Text #2

Max Range: 0.7540. Min Range: -0.7540

Max Act: 0.5658. Min Act: -0.0000

Data Index: 1053256 (The Pile)

Max Activating Token Index: 572

Text #3

Max Range: 0.7540. Min Range: -0.7540

Max Act: 0.5223. Min Act: -0.0000

Data Index: 1619368 (The Pile)

Max Activating Token Index: 681

Text #4

Max Range: 0.7540. Min Range: -0.7540

Max Act: 0.5183. Min Act: -0.0000

Data Index: 1120233 (The Pile)

Max Activating Token Index: 459

Text #5

Max Range: 0.7540. Min Range: -0.7540

Max Act: 0.4230. Min Act: -0.0000

Data Index: 249303 (The Pile)

Max Activating Token Index: 784

Text #6

Max Range: 0.7540. Min Range: -0.7540

Max Act: 0.5508. Min Act: -0.0000

Data Index: 1573496 (The Pile)

Max Activating Token Index: 146

Text #7

Max Range: 0.7540. Min Range: -0.7540

Max Act: 0.4609. Min Act: -0.0000

Data Index: 1994167 (The Pile)

Max Activating Token Index: 1020

Text #8

Max Range: 0.7540. Min Range: -0.7540

Max Act: 0.4458. Min Act: -0.0000

Data Index: 1339933 (The Pile)

Max Activating Token Index: 859

Text #9

Max Range: 0.7540. Min Range: -0.7540

Max Act: 0.4382. Min Act: -0.0000

Data Index: 425948 (The Pile)

Max Activating Token Index: 592

Text #10

Max Range: 0.7540. Min Range: -0.7540

Max Act: 0.4844. Min Act: -0.0000

Data Index: 1589345 (The Pile)

Max Activating Token Index: 97

Text #11

Max Range: 0.7540. Min Range: -0.7540

Max Act: 0.4783. Min Act: -0.0000

Data Index: 98512 (The Pile)

Max Activating Token Index: 1017

Text #12

Max Range: 0.7540. Min Range: -0.7540

Max Act: 0.4595. Min Act: -0.0000

Data Index: 752198 (The Pile)

Max Activating Token Index: 154

Text #13

Max Range: 0.7540. Min Range: -0.7540

Max Act: 0.4548. Min Act: -0.0000

Data Index: 1047904 (The Pile)

Max Activating Token Index: 699

Text #14

Max Range: 0.7540. Min Range: -0.7540

Max Act: 0.4722. Min Act: -0.0000

Data Index: 389743 (The Pile)

Max Activating Token Index: 69

Text #15

Max Range: 0.7540. Min Range: -0.7540

Max Act: 0.4411. Min Act: -0.0000

Data Index: 1486919 (The Pile)

Max Activating Token Index: 187

Text #16

Max Range: 0.7540. Min Range: -0.7540

Max Act: 0.4540. Min Act: -0.0000

Data Index: 865286 (The Pile)

Max Activating Token Index: 189

Text #17

Max Range: 0.7540. Min Range: -0.7540

Max Act: 0.4097. Min Act: -0.0000

Data Index: 1995514 (The Pile)

Max Activating Token Index: 204

Text #18

Max Range: 0.7540. Min Range: -0.7540

Max Act: 0.4357. Min Act: -0.0000

Data Index: 1267574 (The Pile)

Max Activating Token Index: 293

Text #19

Max Range: 0.7540. Min Range: -0.7540

Max Act: 0.3977. Min Act: -0.0000

Data Index: 527866 (The Pile)

Max Activating Token Index: 946