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

Dataset: The Pile

Neuron 3969 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: 0.8478. Min Range: -0.8478

Max Act: 0.8478. Min Act: -0.0000

Data Index: 813782 (The Pile)

Max Activating Token Index: 51

Text #1

Max Range: 0.8478. Min Range: -0.8478

Max Act: 0.7870. Min Act: -0.0000

Data Index: 1143760 (The Pile)

Max Activating Token Index: 397

Text #2

Max Range: 0.8478. Min Range: -0.8478

Max Act: 0.7903. Min Act: -0.0000

Data Index: 603447 (The Pile)

Max Activating Token Index: 89

Text #3

Max Range: 0.8478. Min Range: -0.8478

Max Act: 0.8033. Min Act: -0.0000

Data Index: 1884166 (The Pile)

Max Activating Token Index: 45

Text #4

Max Range: 0.8478. Min Range: -0.8478

Max Act: 0.7752. Min Act: -0.0000

Data Index: 121497 (The Pile)

Max Activating Token Index: 349

Text #5

Max Range: 0.8478. Min Range: -0.8478

Max Act: 0.6918. Min Act: -0.0000

Data Index: 1916013 (The Pile)

Max Activating Token Index: 208

Text #6

Max Range: 0.8478. Min Range: -0.8478

Max Act: 0.7407. Min Act: -0.0000

Data Index: 615134 (The Pile)

Max Activating Token Index: 240

Text #7

Max Range: 0.8478. Min Range: -0.8478

Max Act: 0.7547. Min Act: -0.0000

Data Index: 705706 (The Pile)

Max Activating Token Index: 314

Text #8

Max Range: 0.8478. Min Range: -0.8478

Max Act: 0.6613. Min Act: -0.0000

Data Index: 1870392 (The Pile)

Max Activating Token Index: 170

Text #9

Max Range: 0.8478. Min Range: -0.8478

Max Act: 0.6797. Min Act: -0.0000

Data Index: 757137 (The Pile)

Max Activating Token Index: 361

Text #10

Max Range: 0.8478. Min Range: -0.8478

Max Act: 0.7319. Min Act: -0.0000

Data Index: 789374 (The Pile)

Max Activating Token Index: 145

Text #11

Max Range: 0.8478. Min Range: -0.8478

Max Act: 0.7090. Min Act: -0.0000

Data Index: 1964938 (The Pile)

Max Activating Token Index: 95

Text #12

Max Range: 0.8478. Min Range: -0.8478

Max Act: 0.6567. Min Act: -0.0000

Data Index: 1939996 (The Pile)

Max Activating Token Index: 69

Text #13

Max Range: 0.8478. Min Range: -0.8478

Max Act: 0.6825. Min Act: -0.0000

Data Index: 1973008 (The Pile)

Max Activating Token Index: 120

Text #14

Max Range: 0.8478. Min Range: -0.8478

Max Act: 0.6209. Min Act: -0.0000

Data Index: 747638 (The Pile)

Max Activating Token Index: 432

Text #15

Max Range: 0.8478. Min Range: -0.8478

Max Act: 0.6106. Min Act: -0.0000

Data Index: 1991279 (The Pile)

Max Activating Token Index: 86

Text #16

Max Range: 0.8478. Min Range: -0.8478

Max Act: 0.6160. Min Act: -0.0000

Data Index: 1263421 (The Pile)

Max Activating Token Index: 35

Text #17

Max Range: 0.8478. Min Range: -0.8478

Max Act: 0.6275. Min Act: -0.0000

Data Index: 1289425 (The Pile)

Max Activating Token Index: 24

Text #18

Max Range: 0.8478. Min Range: -0.8478

Max Act: 0.6551. Min Act: -0.0000

Data Index: 1482568 (The Pile)

Max Activating Token Index: 444

Text #19

Max Range: 0.8478. Min Range: -0.8478

Max Act: 0.6092. Min Act: -0.0000

Data Index: 1668091 (The Pile)

Max Activating Token Index: 530