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

Dataset: The Pile

Neuron 4691 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: 5.9953. Min Range: -5.9953

Max Act: 5.4612. Min Act: -0.0000

Data Index: 1140134 (The Pile)

Max Activating Token Index: 192

Text #1

Max Range: 5.9953. Min Range: -5.9953

Max Act: 5.6845. Min Act: -0.0000

Data Index: 1063401 (The Pile)

Max Activating Token Index: 343

Text #2

Max Range: 5.9953. Min Range: -5.9953

Max Act: 5.5933. Min Act: -0.0000

Data Index: 1229568 (The Pile)

Max Activating Token Index: 618

Text #3

Max Range: 5.9953. Min Range: -5.9953

Max Act: 5.6466. Min Act: -0.0000

Data Index: 39548 (The Pile)

Max Activating Token Index: 788

Text #4

Max Range: 5.9953. Min Range: -5.9953

Max Act: 5.3286. Min Act: -0.0000

Data Index: 235505 (The Pile)

Max Activating Token Index: 521

Text #5

Max Range: 5.9953. Min Range: -5.9953

Max Act: 5.9953. Min Act: -0.0000

Data Index: 629499 (The Pile)

Max Activating Token Index: 183

Text #6

Max Range: 5.9953. Min Range: -5.9953

Max Act: 5.3443. Min Act: -0.0000

Data Index: 1380430 (The Pile)

Max Activating Token Index: 601

Text #7

Max Range: 5.9953. Min Range: -5.9953

Max Act: 5.3286. Min Act: -0.0000

Data Index: 579022 (The Pile)

Max Activating Token Index: 663

Text #8

Max Range: 5.9953. Min Range: -5.9953

Max Act: 5.0265. Min Act: -0.0000

Data Index: 798785 (The Pile)

Max Activating Token Index: 60

Text #9

Max Range: 5.9953. Min Range: -5.9953

Max Act: 5.6505. Min Act: -0.0000

Data Index: 1776399 (The Pile)

Max Activating Token Index: 576

Text #10

Max Range: 5.9953. Min Range: -5.9953

Max Act: 5.1253. Min Act: -0.0000

Data Index: 812930 (The Pile)

Max Activating Token Index: 453

Text #11

Max Range: 5.9953. Min Range: -5.9953

Max Act: 5.1829. Min Act: -0.0000

Data Index: 83105 (The Pile)

Max Activating Token Index: 142

Text #12

Max Range: 5.9953. Min Range: -5.9953

Max Act: 5.3691. Min Act: -0.0000

Data Index: 504314 (The Pile)

Max Activating Token Index: 321

Text #13

Max Range: 5.9953. Min Range: -5.9953

Max Act: 5.3206. Min Act: -0.0000

Data Index: 721705 (The Pile)

Max Activating Token Index: 819

Text #14

Max Range: 5.9953. Min Range: -5.9953

Max Act: 5.1370. Min Act: -0.0000

Data Index: 1272842 (The Pile)

Max Activating Token Index: 551

Text #15

Max Range: 5.9953. Min Range: -5.9953

Max Act: 4.9656. Min Act: -0.0000

Data Index: 1812868 (The Pile)

Max Activating Token Index: 441

Text #16

Max Range: 5.9953. Min Range: -5.9953

Max Act: 5.3189. Min Act: -0.0000

Data Index: 710326 (The Pile)

Max Activating Token Index: 41

Text #17

Max Range: 5.9953. Min Range: -5.9953

Max Act: 5.1005. Min Act: -0.0000

Data Index: 958115 (The Pile)

Max Activating Token Index: 607

Text #18

Max Range: 5.9953. Min Range: -5.9953

Max Act: 4.8889. Min Act: -0.0000

Data Index: 1025655 (The Pile)

Max Activating Token Index: 42

Text #19

Max Range: 5.9953. Min Range: -5.9953

Max Act: 4.6658. Min Act: -0.0000

Data Index: 8535 (The Pile)

Max Activating Token Index: 872