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

Dataset: The Pile

Neuron 2063 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5106. Min Range: -0.5106

Max Act: 0.5106. Min Act: -0.0000

Data Index: 1416696 (The Pile)

Max Activating Token Index: 278

Text #1

Max Range: 0.5106. Min Range: -0.5106

Max Act: 0.5017. Min Act: -0.0000

Data Index: 823376 (The Pile)

Max Activating Token Index: 898

Text #2

Max Range: 0.5106. Min Range: -0.5106

Max Act: 0.4807. Min Act: -0.0000

Data Index: 1928410 (The Pile)

Max Activating Token Index: 40

Text #3

Max Range: 0.5106. Min Range: -0.5106

Max Act: 0.4493. Min Act: -0.0000

Data Index: 1637051 (The Pile)

Max Activating Token Index: 130

Text #4

Max Range: 0.5106. Min Range: -0.5106

Max Act: 0.4426. Min Act: -0.0000

Data Index: 1315341 (The Pile)

Max Activating Token Index: 800

Text #5

Max Range: 0.5106. Min Range: -0.5106

Max Act: 0.4033. Min Act: -0.0000

Data Index: 102518 (The Pile)

Max Activating Token Index: 355

Text #6

Max Range: 0.5106. Min Range: -0.5106

Max Act: 0.3786. Min Act: -0.0000

Data Index: 333579 (The Pile)

Max Activating Token Index: 867

Text #7

Max Range: 0.5106. Min Range: -0.5106

Max Act: 0.4140. Min Act: -0.0000

Data Index: 563884 (The Pile)

Max Activating Token Index: 166

Text #8

Max Range: 0.5106. Min Range: -0.5106

Max Act: 0.3914. Min Act: -0.0000

Data Index: 811348 (The Pile)

Max Activating Token Index: 166

Text #9

Max Range: 0.5106. Min Range: -0.5106

Max Act: 0.3931. Min Act: -0.0000

Data Index: 1039821 (The Pile)

Max Activating Token Index: 418

Text #10

Max Range: 0.5106. Min Range: -0.5106

Max Act: 0.3890. Min Act: -0.0000

Data Index: 769620 (The Pile)

Max Activating Token Index: 1015

Text #11

Max Range: 0.5106. Min Range: -0.5106

Max Act: 0.3647. Min Act: -0.0000

Data Index: 1328601 (The Pile)

Max Activating Token Index: 196

Text #12

Max Range: 0.5106. Min Range: -0.5106

Max Act: 0.3990. Min Act: -0.0000

Data Index: 1685271 (The Pile)

Max Activating Token Index: 412

Text #13

Max Range: 0.5106. Min Range: -0.5106

Max Act: 0.3685. Min Act: -0.0000

Data Index: 1776707 (The Pile)

Max Activating Token Index: 293

Text #14

Max Range: 0.5106. Min Range: -0.5106

Max Act: 0.3644. Min Act: -0.0000

Data Index: 1662096 (The Pile)

Max Activating Token Index: 31

Text #15

Max Range: 0.5106. Min Range: -0.5106

Max Act: 0.3776. Min Act: -0.0000

Data Index: 584444 (The Pile)

Max Activating Token Index: 709

Text #16

Max Range: 0.5106. Min Range: -0.5106

Max Act: 0.4048. Min Act: -0.0000

Data Index: 334684 (The Pile)

Max Activating Token Index: 126

Text #17

Max Range: 0.5106. Min Range: -0.5106

Max Act: 0.3393. Min Act: -0.0000

Data Index: 69527 (The Pile)

Max Activating Token Index: 762

Text #18

Max Range: 0.5106. Min Range: -0.5106

Max Act: 0.3884. Min Act: -0.0000

Data Index: 1676994 (The Pile)

Max Activating Token Index: 301

Text #19

Max Range: 0.5106. Min Range: -0.5106

Max Act: 0.3734. Min Act: -0.0000

Data Index: 736186 (The Pile)

Max Activating Token Index: 369