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

Dataset: The Pile

Neuron 3224 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.6605. Min Range: -1.6605

Max Act: 1.6605. Min Act: -0.0000

Data Index: 737108 (The Pile)

Max Activating Token Index: 361

Text #1

Max Range: 1.6605. Min Range: -1.6605

Max Act: 1.6089. Min Act: -0.0000

Data Index: 1346628 (The Pile)

Max Activating Token Index: 337

Text #2

Max Range: 1.6605. Min Range: -1.6605

Max Act: 1.5949. Min Act: -0.0000

Data Index: 1472195 (The Pile)

Max Activating Token Index: 72

Text #3

Max Range: 1.6605. Min Range: -1.6605

Max Act: 1.4419. Min Act: -0.0000

Data Index: 543680 (The Pile)

Max Activating Token Index: 386

Text #4

Max Range: 1.6605. Min Range: -1.6605

Max Act: 1.4685. Min Act: -0.0000

Data Index: 969051 (The Pile)

Max Activating Token Index: 160

Text #5

Max Range: 1.6605. Min Range: -1.6605

Max Act: 1.3404. Min Act: -0.0000

Data Index: 35464 (The Pile)

Max Activating Token Index: 262

Text #6

Max Range: 1.6605. Min Range: -1.6605

Max Act: 1.3146. Min Act: -0.0000

Data Index: 1608489 (The Pile)

Max Activating Token Index: 279

Text #7

Max Range: 1.6605. Min Range: -1.6605

Max Act: 1.2840. Min Act: -0.0000

Data Index: 1909941 (The Pile)

Max Activating Token Index: 495

Text #8

Max Range: 1.6605. Min Range: -1.6605

Max Act: 1.0746. Min Act: -0.0000

Data Index: 951165 (The Pile)

Max Activating Token Index: 971

Text #9

Max Range: 1.6605. Min Range: -1.6605

Max Act: 1.2441. Min Act: -0.0000

Data Index: 481333 (The Pile)

Max Activating Token Index: 638

Text #10

Max Range: 1.6605. Min Range: -1.6605

Max Act: 1.0466. Min Act: -0.0000

Data Index: 242242 (The Pile)

Max Activating Token Index: 345

Text #11

Max Range: 1.6605. Min Range: -1.6605

Max Act: 1.1438. Min Act: -0.0000

Data Index: 1703210 (The Pile)

Max Activating Token Index: 997

Text #12

Max Range: 1.6605. Min Range: -1.6605

Max Act: 1.1886. Min Act: -0.0000

Data Index: 1146241 (The Pile)

Max Activating Token Index: 988

Text #13

Max Range: 1.6605. Min Range: -1.6605

Max Act: 1.1080. Min Act: -0.0000

Data Index: 1916828 (The Pile)

Max Activating Token Index: 563

Text #14

Max Range: 1.6605. Min Range: -1.6605

Max Act: 1.1106. Min Act: -0.0000

Data Index: 1068790 (The Pile)

Max Activating Token Index: 121

Text #15

Max Range: 1.6605. Min Range: -1.6605

Max Act: 1.2240. Min Act: -0.0000

Data Index: 1632163 (The Pile)

Max Activating Token Index: 462

Text #16

Max Range: 1.6605. Min Range: -1.6605

Max Act: 1.1475. Min Act: -0.0000

Data Index: 670077 (The Pile)

Max Activating Token Index: 563

Text #17

Max Range: 1.6605. Min Range: -1.6605

Max Act: 1.1139. Min Act: -0.0000

Data Index: 1769495 (The Pile)

Max Activating Token Index: 359

Text #18

Max Range: 1.6605. Min Range: -1.6605

Max Act: 1.1701. Min Act: -0.0000

Data Index: 450578 (The Pile)

Max Activating Token Index: 533

Text #19

Max Range: 1.6605. Min Range: -1.6605

Max Act: 1.0852. Min Act: -0.0000

Data Index: 1577983 (The Pile)

Max Activating Token Index: 875