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

Dataset: The Pile

Neuron 3290 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: 1.2074. Min Range: -1.2074

Max Act: 1.2074. Min Act: -0.0000

Data Index: 1098341 (The Pile)

Max Activating Token Index: 239

Text #1

Max Range: 1.2074. Min Range: -1.2074

Max Act: 1.0089. Min Act: -0.0000

Data Index: 344147 (The Pile)

Max Activating Token Index: 315

Text #2

Max Range: 1.2074. Min Range: -1.2074

Max Act: 0.9592. Min Act: -0.0000

Data Index: 1272842 (The Pile)

Max Activating Token Index: 112

Text #3

Max Range: 1.2074. Min Range: -1.2074

Max Act: 0.8485. Min Act: -0.0000

Data Index: 421832 (The Pile)

Max Activating Token Index: 786

Text #4

Max Range: 1.2074. Min Range: -1.2074

Max Act: 0.7821. Min Act: -0.0000

Data Index: 387664 (The Pile)

Max Activating Token Index: 911

Text #5

Max Range: 1.2074. Min Range: -1.2074

Max Act: 0.8084. Min Act: -0.0000

Data Index: 1175733 (The Pile)

Max Activating Token Index: 25

Text #6

Max Range: 1.2074. Min Range: -1.2074

Max Act: 0.7538. Min Act: -0.0000

Data Index: 1671974 (The Pile)

Max Activating Token Index: 314

Text #7

Max Range: 1.2074. Min Range: -1.2074

Max Act: 0.7484. Min Act: -0.0000

Data Index: 992698 (The Pile)

Max Activating Token Index: 571

Text #8

Max Range: 1.2074. Min Range: -1.2074

Max Act: 0.6947. Min Act: -0.0000

Data Index: 1832828 (The Pile)

Max Activating Token Index: 317

Text #9

Max Range: 1.2074. Min Range: -1.2074

Max Act: 0.6233. Min Act: -0.0000

Data Index: 1571023 (The Pile)

Max Activating Token Index: 891

Text #10

Max Range: 1.2074. Min Range: -1.2074

Max Act: 0.6828. Min Act: -0.0000

Data Index: 1346172 (The Pile)

Max Activating Token Index: 545

Text #11

Max Range: 1.2074. Min Range: -1.2074

Max Act: 0.6711. Min Act: -0.0000

Data Index: 1088176 (The Pile)

Max Activating Token Index: 1006

Text #12

Max Range: 1.2074. Min Range: -1.2074

Max Act: 0.6704. Min Act: -0.0000

Data Index: 1329747 (The Pile)

Max Activating Token Index: 975

Text #13

Max Range: 1.2074. Min Range: -1.2074

Max Act: 0.7100. Min Act: -0.0000

Data Index: 136274 (The Pile)

Max Activating Token Index: 63

Text #14

Max Range: 1.2074. Min Range: -1.2074

Max Act: 0.6761. Min Act: -0.0000

Data Index: 608285 (The Pile)

Max Activating Token Index: 28

Text #15

Max Range: 1.2074. Min Range: -1.2074

Max Act: 0.6625. Min Act: -0.0000

Data Index: 1339778 (The Pile)

Max Activating Token Index: 39

Text #16

Max Range: 1.2074. Min Range: -1.2074

Max Act: 0.6347. Min Act: -0.0000

Data Index: 99083 (The Pile)

Max Activating Token Index: 340

Text #17

Max Range: 1.2074. Min Range: -1.2074

Max Act: 0.6027. Min Act: -0.0000

Data Index: 724317 (The Pile)

Max Activating Token Index: 838

Text #18

Max Range: 1.2074. Min Range: -1.2074

Max Act: 0.6291. Min Act: -0.0000

Data Index: 619765 (The Pile)

Max Activating Token Index: 376

Text #19

Max Range: 1.2074. Min Range: -1.2074

Max Act: 0.6623. Min Act: -0.0000

Data Index: 1701323 (The Pile)

Max Activating Token Index: 748