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

Dataset: The Pile

Neuron 3450 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7864. Min Range: -0.7864

Max Act: 0.7864. Min Act: -0.0000

Data Index: 1143443 (The Pile)

Max Activating Token Index: 972

Text #1

Max Range: 0.7864. Min Range: -0.7864

Max Act: 0.7527. Min Act: -0.0000

Data Index: 763092 (The Pile)

Max Activating Token Index: 74

Text #2

Max Range: 0.7864. Min Range: -0.7864

Max Act: 0.6694. Min Act: -0.0000

Data Index: 372209 (The Pile)

Max Activating Token Index: 923

Text #3

Max Range: 0.7864. Min Range: -0.7864

Max Act: 0.6794. Min Act: -0.0000

Data Index: 1729964 (The Pile)

Max Activating Token Index: 920

Text #4

Max Range: 0.7864. Min Range: -0.7864

Max Act: 0.6474. Min Act: -0.0000

Data Index: 856775 (The Pile)

Max Activating Token Index: 787

Text #5

Max Range: 0.7864. Min Range: -0.7864

Max Act: 0.6313. Min Act: -0.0000

Data Index: 356441 (The Pile)

Max Activating Token Index: 361

Text #6

Max Range: 0.7864. Min Range: -0.7864

Max Act: 0.6081. Min Act: -0.0000

Data Index: 1490701 (The Pile)

Max Activating Token Index: 899

Text #7

Max Range: 0.7864. Min Range: -0.7864

Max Act: 0.6353. Min Act: -0.0000

Data Index: 921487 (The Pile)

Max Activating Token Index: 494

Text #8

Max Range: 0.7864. Min Range: -0.7864

Max Act: 0.6078. Min Act: -0.0000

Data Index: 857864 (The Pile)

Max Activating Token Index: 14

Text #9

Max Range: 0.7864. Min Range: -0.7864

Max Act: 0.6364. Min Act: -0.0000

Data Index: 1371319 (The Pile)

Max Activating Token Index: 1003

Text #10

Max Range: 0.7864. Min Range: -0.7864

Max Act: 0.5893. Min Act: -0.0000

Data Index: 383811 (The Pile)

Max Activating Token Index: 749

Text #11

Max Range: 0.7864. Min Range: -0.7864

Max Act: 0.5697. Min Act: -0.0000

Data Index: 916290 (The Pile)

Max Activating Token Index: 939

Text #12

Max Range: 0.7864. Min Range: -0.7864

Max Act: 0.5614. Min Act: -0.0000

Data Index: 1373403 (The Pile)

Max Activating Token Index: 321

Text #13

Max Range: 0.7864. Min Range: -0.7864

Max Act: 0.5605. Min Act: -0.0000

Data Index: 1345926 (The Pile)

Max Activating Token Index: 285

Text #14

Max Range: 0.7864. Min Range: -0.7864

Max Act: 0.5909. Min Act: -0.0000

Data Index: 710931 (The Pile)

Max Activating Token Index: 699

Text #15

Max Range: 0.7864. Min Range: -0.7864

Max Act: 0.5407. Min Act: -0.0000

Data Index: 1486389 (The Pile)

Max Activating Token Index: 272

Text #16

Max Range: 0.7864. Min Range: -0.7864

Max Act: 0.6231. Min Act: -0.0000

Data Index: 1009103 (The Pile)

Max Activating Token Index: 860

Text #17

Max Range: 0.7864. Min Range: -0.7864

Max Act: 0.5805. Min Act: -0.0000

Data Index: 522482 (The Pile)

Max Activating Token Index: 446

Text #18

Max Range: 0.7864. Min Range: -0.7864

Max Act: 0.5416. Min Act: -0.0000

Data Index: 147915 (The Pile)

Max Activating Token Index: 770

Text #19

Max Range: 0.7864. Min Range: -0.7864

Max Act: 0.5742. Min Act: -0.0000

Data Index: 838831 (The Pile)

Max Activating Token Index: 1007