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

Dataset: The Pile

Neuron 2505 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8891. Min Range: -0.8891

Max Act: 0.8891. Min Act: -0.0000

Data Index: 1372754 (The Pile)

Max Activating Token Index: 351

Text #1

Max Range: 0.8891. Min Range: -0.8891

Max Act: 0.8264. Min Act: -0.0000

Data Index: 1737390 (The Pile)

Max Activating Token Index: 283

Text #2

Max Range: 0.8891. Min Range: -0.8891

Max Act: 0.8136. Min Act: -0.0000

Data Index: 513112 (The Pile)

Max Activating Token Index: 779

Text #3

Max Range: 0.8891. Min Range: -0.8891

Max Act: 0.7900. Min Act: -0.0000

Data Index: 1004918 (The Pile)

Max Activating Token Index: 701

Text #4

Max Range: 0.8891. Min Range: -0.8891

Max Act: 0.7280. Min Act: -0.0000

Data Index: 1978399 (The Pile)

Max Activating Token Index: 869

Text #5

Max Range: 0.8891. Min Range: -0.8891

Max Act: 0.6566. Min Act: -0.0000

Data Index: 866538 (The Pile)

Max Activating Token Index: 603

Text #6

Max Range: 0.8891. Min Range: -0.8891

Max Act: 0.6524. Min Act: -0.0000

Data Index: 558322 (The Pile)

Max Activating Token Index: 397

Text #7

Max Range: 0.8891. Min Range: -0.8891

Max Act: 0.6462. Min Act: -0.0000

Data Index: 506373 (The Pile)

Max Activating Token Index: 290

Text #8

Max Range: 0.8891. Min Range: -0.8891

Max Act: 0.6033. Min Act: -0.0000

Data Index: 994200 (The Pile)

Max Activating Token Index: 491

Text #9

Max Range: 0.8891. Min Range: -0.8891

Max Act: 0.5381. Min Act: -0.0000

Data Index: 1849285 (The Pile)

Max Activating Token Index: 227

Text #10

Max Range: 0.8891. Min Range: -0.8891

Max Act: 0.5795. Min Act: -0.0000

Data Index: 1106970 (The Pile)

Max Activating Token Index: 960

Text #11

Max Range: 0.8891. Min Range: -0.8891

Max Act: 0.5648. Min Act: -0.0000

Data Index: 1068595 (The Pile)

Max Activating Token Index: 90

Text #12

Max Range: 0.8891. Min Range: -0.8891

Max Act: 0.5573. Min Act: -0.0000

Data Index: 608900 (The Pile)

Max Activating Token Index: 826

Text #13

Max Range: 0.8891. Min Range: -0.8891

Max Act: 0.5546. Min Act: -0.0000

Data Index: 172102 (The Pile)

Max Activating Token Index: 198

Text #14

Max Range: 0.8891. Min Range: -0.8891

Max Act: 0.5556. Min Act: -0.0000

Data Index: 1068223 (The Pile)

Max Activating Token Index: 192

Text #15

Max Range: 0.8891. Min Range: -0.8891

Max Act: 0.5399. Min Act: -0.0000

Data Index: 280432 (The Pile)

Max Activating Token Index: 33

Text #16

Max Range: 0.8891. Min Range: -0.8891

Max Act: 0.5652. Min Act: -0.0000

Data Index: 166236 (The Pile)

Max Activating Token Index: 562

Text #17

Max Range: 0.8891. Min Range: -0.8891

Max Act: 0.5201. Min Act: -0.0000

Data Index: 365815 (The Pile)

Max Activating Token Index: 869

Text #18

Max Range: 0.8891. Min Range: -0.8891

Max Act: 0.5443. Min Act: -0.0000

Data Index: 271746 (The Pile)

Max Activating Token Index: 1000

Text #19

Max Range: 0.8891. Min Range: -0.8891

Max Act: 0.5183. Min Act: -0.0000

Data Index: 1688422 (The Pile)

Max Activating Token Index: 222