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

Dataset: The Pile

Neuron 4039 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: 0.5216. Min Range: -0.5216

Max Act: 0.4857. Min Act: -0.0000

Data Index: 789202 (The Pile)

Max Activating Token Index: 104

Text #1

Max Range: 0.5216. Min Range: -0.5216

Max Act: 0.5216. Min Act: -0.0000

Data Index: 1234292 (The Pile)

Max Activating Token Index: 666

Text #2

Max Range: 0.5216. Min Range: -0.5216

Max Act: 0.4709. Min Act: -0.0000

Data Index: 1143403 (The Pile)

Max Activating Token Index: 484

Text #3

Max Range: 0.5216. Min Range: -0.5216

Max Act: 0.4977. Min Act: -0.0000

Data Index: 636349 (The Pile)

Max Activating Token Index: 958

Text #4

Max Range: 0.5216. Min Range: -0.5216

Max Act: 0.4751. Min Act: -0.0000

Data Index: 229685 (The Pile)

Max Activating Token Index: 602

Text #5

Max Range: 0.5216. Min Range: -0.5216

Max Act: 0.4489. Min Act: -0.0000

Data Index: 1460205 (The Pile)

Max Activating Token Index: 979

Text #6

Max Range: 0.5216. Min Range: -0.5216

Max Act: 0.4587. Min Act: -0.0000

Data Index: 664020 (The Pile)

Max Activating Token Index: 845

Text #7

Max Range: 0.5216. Min Range: -0.5216

Max Act: 0.4445. Min Act: -0.0000

Data Index: 173335 (The Pile)

Max Activating Token Index: 28

Text #8

Max Range: 0.5216. Min Range: -0.5216

Max Act: 0.4410. Min Act: -0.0000

Data Index: 1609635 (The Pile)

Max Activating Token Index: 659

Text #9

Max Range: 0.5216. Min Range: -0.5216

Max Act: 0.4433. Min Act: -0.0000

Data Index: 444628 (The Pile)

Max Activating Token Index: 31

Text #10

Max Range: 0.5216. Min Range: -0.5216

Max Act: 0.4410. Min Act: -0.0000

Data Index: 820235 (The Pile)

Max Activating Token Index: 174

Text #11

Max Range: 0.5216. Min Range: -0.5216

Max Act: 0.4701. Min Act: -0.0000

Data Index: 1348710 (The Pile)

Max Activating Token Index: 106

Text #12

Max Range: 0.5216. Min Range: -0.5216

Max Act: 0.4254. Min Act: -0.0000

Data Index: 144917 (The Pile)

Max Activating Token Index: 584

Text #13

Max Range: 0.5216. Min Range: -0.5216

Max Act: 0.4354. Min Act: -0.0000

Data Index: 266828 (The Pile)

Max Activating Token Index: 720

Text #14

Max Range: 0.5216. Min Range: -0.5216

Max Act: 0.4280. Min Act: -0.0000

Data Index: 440006 (The Pile)

Max Activating Token Index: 187

Text #15

Max Range: 0.5216. Min Range: -0.5216

Max Act: 0.4113. Min Act: -0.0000

Data Index: 785488 (The Pile)

Max Activating Token Index: 370

Text #16

Max Range: 0.5216. Min Range: -0.5216

Max Act: 0.4178. Min Act: -0.0000

Data Index: 1313598 (The Pile)

Max Activating Token Index: 572

Text #17

Max Range: 0.5216. Min Range: -0.5216

Max Act: 0.4178. Min Act: -0.0000

Data Index: 1118093 (The Pile)

Max Activating Token Index: 140

Text #18

Max Range: 0.5216. Min Range: -0.5216

Max Act: 0.4081. Min Act: -0.0000

Data Index: 1587015 (The Pile)

Max Activating Token Index: 331

Text #19

Max Range: 0.5216. Min Range: -0.5216

Max Act: 0.4189. Min Act: -0.0000

Data Index: 1909847 (The Pile)

Max Activating Token Index: 65