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

Dataset: The Pile

Neuron 938 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: 1.2154. Min Range: -1.2154

Max Act: 1.1870. Min Act: -0.0000

Data Index: 1796741 (The Pile)

Max Activating Token Index: 545

Text #1

Max Range: 1.2154. Min Range: -1.2154

Max Act: 1.0915. Min Act: -0.0000

Data Index: 1262307 (The Pile)

Max Activating Token Index: 758

Text #2

Max Range: 1.2154. Min Range: -1.2154

Max Act: 1.1146. Min Act: -0.0000

Data Index: 456051 (The Pile)

Max Activating Token Index: 676

Text #3

Max Range: 1.2154. Min Range: -1.2154

Max Act: 1.1084. Min Act: -0.0000

Data Index: 1272297 (The Pile)

Max Activating Token Index: 450

Text #4

Max Range: 1.2154. Min Range: -1.2154

Max Act: 1.0286. Min Act: -0.0000

Data Index: 930702 (The Pile)

Max Activating Token Index: 1013

Text #5

Max Range: 1.2154. Min Range: -1.2154

Max Act: 1.2154. Min Act: -0.0000

Data Index: 1770428 (The Pile)

Max Activating Token Index: 194

Text #6

Max Range: 1.2154. Min Range: -1.2154

Max Act: 1.1256. Min Act: -0.0000

Data Index: 581157 (The Pile)

Max Activating Token Index: 748

Text #7

Max Range: 1.2154. Min Range: -1.2154

Max Act: 1.0327. Min Act: -0.0000

Data Index: 976862 (The Pile)

Max Activating Token Index: 865

Text #8

Max Range: 1.2154. Min Range: -1.2154

Max Act: 1.1627. Min Act: -0.0000

Data Index: 894415 (The Pile)

Max Activating Token Index: 524

Text #9

Max Range: 1.2154. Min Range: -1.2154

Max Act: 1.0212. Min Act: -0.0000

Data Index: 1110974 (The Pile)

Max Activating Token Index: 385

Text #10

Max Range: 1.2154. Min Range: -1.2154

Max Act: 0.9595. Min Act: -0.0000

Data Index: 283796 (The Pile)

Max Activating Token Index: 468

Text #11

Max Range: 1.2154. Min Range: -1.2154

Max Act: 0.9471. Min Act: -0.0000

Data Index: 116915 (The Pile)

Max Activating Token Index: 256

Text #12

Max Range: 1.2154. Min Range: -1.2154

Max Act: 0.9327. Min Act: -0.0000

Data Index: 666636 (The Pile)

Max Activating Token Index: 878

Text #13

Max Range: 1.2154. Min Range: -1.2154

Max Act: 1.1028. Min Act: -0.0000

Data Index: 1179073 (The Pile)

Max Activating Token Index: 471

Text #14

Max Range: 1.2154. Min Range: -1.2154

Max Act: 0.9132. Min Act: -0.0000

Data Index: 387743 (The Pile)

Max Activating Token Index: 539

Text #15

Max Range: 1.2154. Min Range: -1.2154

Max Act: 0.9320. Min Act: -0.0000

Data Index: 202767 (The Pile)

Max Activating Token Index: 517

Text #16

Max Range: 1.2154. Min Range: -1.2154

Max Act: 0.8510. Min Act: -0.0000

Data Index: 1381487 (The Pile)

Max Activating Token Index: 703

Text #17

Max Range: 1.2154. Min Range: -1.2154

Max Act: 0.9835. Min Act: -0.0000

Data Index: 655909 (The Pile)

Max Activating Token Index: 449

Text #18

Max Range: 1.2154. Min Range: -1.2154

Max Act: 0.9517. Min Act: -0.0000

Data Index: 679175 (The Pile)

Max Activating Token Index: 118

Text #19

Max Range: 1.2154. Min Range: -1.2154

Max Act: 0.8837. Min Act: -0.0000

Data Index: 30838 (The Pile)

Max Activating Token Index: 791