Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3161 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.6599. Min Range: -0.6599

Max Act: 0.6599. Min Act: -0.0000

Data Index: 779830 (The Pile)

Max Activating Token Index: 894

Text #1

Max Range: 0.6599. Min Range: -0.6599

Max Act: 0.5935. Min Act: -0.0000

Data Index: 1762268 (The Pile)

Max Activating Token Index: 993

Text #2

Max Range: 0.6599. Min Range: -0.6599

Max Act: 0.5740. Min Act: -0.0000

Data Index: 552700 (The Pile)

Max Activating Token Index: 820

Text #3

Max Range: 0.6599. Min Range: -0.6599

Max Act: 0.5595. Min Act: -0.0000

Data Index: 1266775 (The Pile)

Max Activating Token Index: 929

Text #4

Max Range: 0.6599. Min Range: -0.6599

Max Act: 0.5506. Min Act: -0.0000

Data Index: 1620452 (The Pile)

Max Activating Token Index: 333

Text #5

Max Range: 0.6599. Min Range: -0.6599

Max Act: 0.5636. Min Act: -0.0000

Data Index: 348543 (The Pile)

Max Activating Token Index: 1021

Text #6

Max Range: 0.6599. Min Range: -0.6599

Max Act: 0.5572. Min Act: -0.0000

Data Index: 298929 (The Pile)

Max Activating Token Index: 169

Text #7

Max Range: 0.6599. Min Range: -0.6599

Max Act: 0.5533. Min Act: -0.0000

Data Index: 1195719 (The Pile)

Max Activating Token Index: 1007

Text #8

Max Range: 0.6599. Min Range: -0.6599

Max Act: 0.4879. Min Act: -0.0000

Data Index: 328852 (The Pile)

Max Activating Token Index: 149

Text #9

Max Range: 0.6599. Min Range: -0.6599

Max Act: 0.3928. Min Act: -0.0000

Data Index: 593087 (The Pile)

Max Activating Token Index: 396

Text #10

Max Range: 0.6599. Min Range: -0.6599

Max Act: 0.4604. Min Act: -0.0000

Data Index: 525343 (The Pile)

Max Activating Token Index: 879

Text #11

Max Range: 0.6599. Min Range: -0.6599

Max Act: 0.4956. Min Act: -0.0000

Data Index: 616026 (The Pile)

Max Activating Token Index: 533

Text #12

Max Range: 0.6599. Min Range: -0.6599

Max Act: 0.5295. Min Act: -0.0000

Data Index: 1292113 (The Pile)

Max Activating Token Index: 360

Text #13

Max Range: 0.6599. Min Range: -0.6599

Max Act: 0.4611. Min Act: -0.0000

Data Index: 221914 (The Pile)

Max Activating Token Index: 300

Text #14

Max Range: 0.6599. Min Range: -0.6599

Max Act: 0.5141. Min Act: -0.0000

Data Index: 1990384 (The Pile)

Max Activating Token Index: 325

Text #15

Max Range: 0.6599. Min Range: -0.6599

Max Act: 0.4998. Min Act: -0.0000

Data Index: 1895984 (The Pile)

Max Activating Token Index: 802

Text #16

Max Range: 0.6599. Min Range: -0.6599

Max Act: 0.4102. Min Act: -0.0000

Data Index: 423666 (The Pile)

Max Activating Token Index: 793

Text #17

Max Range: 0.6599. Min Range: -0.6599

Max Act: 0.4265. Min Act: -0.0000

Data Index: 1828496 (The Pile)

Max Activating Token Index: 952

Text #18

Max Range: 0.6599. Min Range: -0.6599

Max Act: 0.4827. Min Act: -0.0000

Data Index: 467442 (The Pile)

Max Activating Token Index: 885

Text #19

Max Range: 0.6599. Min Range: -0.6599

Max Act: 0.5063. Min Act: -0.0000

Data Index: 451117 (The Pile)

Max Activating Token Index: 630