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

Dataset: The Pile

Neuron 4363 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: 0.3186. Min Range: -0.3186

Max Act: 0.3186. Min Act: -0.0000

Data Index: 1922636 (The Pile)

Max Activating Token Index: 963

Text #1

Max Range: 0.3186. Min Range: -0.3186

Max Act: 0.2279. Min Act: -0.0000

Data Index: 1663349 (The Pile)

Max Activating Token Index: 107

Text #2

Max Range: 0.3186. Min Range: -0.3186

Max Act: 0.2260. Min Act: -0.0000

Data Index: 929493 (The Pile)

Max Activating Token Index: 427

Text #3

Max Range: 0.3186. Min Range: -0.3186

Max Act: 0.2109. Min Act: -0.0000

Data Index: 1415546 (The Pile)

Max Activating Token Index: 647

Text #4

Max Range: 0.3186. Min Range: -0.3186

Max Act: 0.2212. Min Act: -0.0000

Data Index: 1796339 (The Pile)

Max Activating Token Index: 338

Text #5

Max Range: 0.3186. Min Range: -0.3186

Max Act: 0.1985. Min Act: -0.0000

Data Index: 359669 (The Pile)

Max Activating Token Index: 363

Text #6

Max Range: 0.3186. Min Range: -0.3186

Max Act: 0.2075. Min Act: -0.0000

Data Index: 870210 (The Pile)

Max Activating Token Index: 156

Text #7

Max Range: 0.3186. Min Range: -0.3186

Max Act: 0.1603. Min Act: -0.0000

Data Index: 614051 (The Pile)

Max Activating Token Index: 949

Text #8

Max Range: 0.3186. Min Range: -0.3186

Max Act: 0.1729. Min Act: -0.0000

Data Index: 562925 (The Pile)

Max Activating Token Index: 889

Text #9

Max Range: 0.3186. Min Range: -0.3186

Max Act: 0.1753. Min Act: -0.0000

Data Index: 814988 (The Pile)

Max Activating Token Index: 968

Text #10

Max Range: 0.3186. Min Range: -0.3186

Max Act: 0.1546. Min Act: -0.0000

Data Index: 1547896 (The Pile)

Max Activating Token Index: 1022

Text #11

Max Range: 0.3186. Min Range: -0.3186

Max Act: 0.1556. Min Act: -0.0000

Data Index: 1006102 (The Pile)

Max Activating Token Index: 453

Text #12

Max Range: 0.3186. Min Range: -0.3186

Max Act: 0.1602. Min Act: -0.0000

Data Index: 864386 (The Pile)

Max Activating Token Index: 574

Text #13

Max Range: 0.3186. Min Range: -0.3186

Max Act: 0.1778. Min Act: -0.0000

Data Index: 670127 (The Pile)

Max Activating Token Index: 980

Text #14

Max Range: 0.3186. Min Range: -0.3186

Max Act: 0.1493. Min Act: -0.0000

Data Index: 432858 (The Pile)

Max Activating Token Index: 927

Text #15

Max Range: 0.3186. Min Range: -0.3186

Max Act: 0.1651. Min Act: -0.0000

Data Index: 1398115 (The Pile)

Max Activating Token Index: 577

Text #16

Max Range: 0.3186. Min Range: -0.3186

Max Act: 0.1482. Min Act: -0.0000

Data Index: 1722621 (The Pile)

Max Activating Token Index: 240

Text #17

Max Range: 0.3186. Min Range: -0.3186

Max Act: 0.1448. Min Act: -0.0000

Data Index: 937375 (The Pile)

Max Activating Token Index: 304

Text #18

Max Range: 0.3186. Min Range: -0.3186

Max Act: 0.1426. Min Act: -0.0000

Data Index: 1697274 (The Pile)

Max Activating Token Index: 148

Text #19

Max Range: 0.3186. Min Range: -0.3186

Max Act: 0.1411. Min Act: -0.0000

Data Index: 24315 (The Pile)

Max Activating Token Index: 854