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

Dataset: The Pile

Neuron 251 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: 1.6568. Min Range: -1.6568

Max Act: 1.6568. Min Act: -0.0000

Data Index: 1365933 (The Pile)

Max Activating Token Index: 90

Text #1

Max Range: 1.6568. Min Range: -1.6568

Max Act: 1.5583. Min Act: -0.0000

Data Index: 1937351 (The Pile)

Max Activating Token Index: 363

Text #2

Max Range: 1.6568. Min Range: -1.6568

Max Act: 1.4212. Min Act: -0.0000

Data Index: 50162 (The Pile)

Max Activating Token Index: 276

Text #3

Max Range: 1.6568. Min Range: -1.6568

Max Act: 1.2159. Min Act: -0.0000

Data Index: 104916 (The Pile)

Max Activating Token Index: 776

Text #4

Max Range: 1.6568. Min Range: -1.6568

Max Act: 1.3799. Min Act: -0.0000

Data Index: 879437 (The Pile)

Max Activating Token Index: 538

Text #5

Max Range: 1.6568. Min Range: -1.6568

Max Act: 1.2484. Min Act: -0.0000

Data Index: 963164 (The Pile)

Max Activating Token Index: 504

Text #6

Max Range: 1.6568. Min Range: -1.6568

Max Act: 1.4027. Min Act: -0.0000

Data Index: 324089 (The Pile)

Max Activating Token Index: 632

Text #7

Max Range: 1.6568. Min Range: -1.6568

Max Act: 1.1982. Min Act: -0.0000

Data Index: 434944 (The Pile)

Max Activating Token Index: 825

Text #8

Max Range: 1.6568. Min Range: -1.6568

Max Act: 1.1290. Min Act: -0.0000

Data Index: 490292 (The Pile)

Max Activating Token Index: 1007

Text #9

Max Range: 1.6568. Min Range: -1.6568

Max Act: 1.0807. Min Act: -0.0000

Data Index: 835990 (The Pile)

Max Activating Token Index: 657

Text #10

Max Range: 1.6568. Min Range: -1.6568

Max Act: 1.1823. Min Act: -0.0000

Data Index: 1437595 (The Pile)

Max Activating Token Index: 136

Text #11

Max Range: 1.6568. Min Range: -1.6568

Max Act: 1.0619. Min Act: -0.0000

Data Index: 1952043 (The Pile)

Max Activating Token Index: 243

Text #12

Max Range: 1.6568. Min Range: -1.6568

Max Act: 1.0315. Min Act: -0.0000

Data Index: 1715933 (The Pile)

Max Activating Token Index: 147

Text #13

Max Range: 1.6568. Min Range: -1.6568

Max Act: 1.0629. Min Act: -0.0000

Data Index: 1184582 (The Pile)

Max Activating Token Index: 676

Text #14

Max Range: 1.6568. Min Range: -1.6568

Max Act: 0.9848. Min Act: -0.0000

Data Index: 1251501 (The Pile)

Max Activating Token Index: 19

Text #15

Max Range: 1.6568. Min Range: -1.6568

Max Act: 0.8865. Min Act: -0.0000

Data Index: 156202 (The Pile)

Max Activating Token Index: 407

Text #16

Max Range: 1.6568. Min Range: -1.6568

Max Act: 0.8558. Min Act: -0.0000

Data Index: 1063720 (The Pile)

Max Activating Token Index: 34

Text #17

Max Range: 1.6568. Min Range: -1.6568

Max Act: 0.8537. Min Act: -0.0000

Data Index: 1385963 (The Pile)

Max Activating Token Index: 328

Text #18

Max Range: 1.6568. Min Range: -1.6568

Max Act: 0.7695. Min Act: -0.0000

Data Index: 1414250 (The Pile)

Max Activating Token Index: 349

Text #19

Max Range: 1.6568. Min Range: -1.6568

Max Act: 0.8189. Min Act: -0.0000

Data Index: 960696 (The Pile)

Max Activating Token Index: 818