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

Dataset: The Pile

Neuron 1296 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: 3.9488. Min Range: -3.9488

Max Act: 3.8023. Min Act: -0.0000

Data Index: 1989514 (The Pile)

Max Activating Token Index: 455

Text #1

Max Range: 3.9488. Min Range: -3.9488

Max Act: 3.3173. Min Act: -0.0000

Data Index: 15320 (The Pile)

Max Activating Token Index: 365

Text #2

Max Range: 3.9488. Min Range: -3.9488

Max Act: 3.9488. Min Act: -0.0000

Data Index: 1430315 (The Pile)

Max Activating Token Index: 834

Text #3

Max Range: 3.9488. Min Range: -3.9488

Max Act: 3.6348. Min Act: -0.0000

Data Index: 1579765 (The Pile)

Max Activating Token Index: 988

Text #4

Max Range: 3.9488. Min Range: -3.9488

Max Act: 3.7174. Min Act: -0.0000

Data Index: 536883 (The Pile)

Max Activating Token Index: 738

Text #5

Max Range: 3.9488. Min Range: -3.9488

Max Act: 3.5666. Min Act: -0.0000

Data Index: 564401 (The Pile)

Max Activating Token Index: 188

Text #6

Max Range: 3.9488. Min Range: -3.9488

Max Act: 3.5920. Min Act: -0.0000

Data Index: 1446166 (The Pile)

Max Activating Token Index: 287

Text #7

Max Range: 3.9488. Min Range: -3.9488

Max Act: 2.7690. Min Act: -0.0000

Data Index: 983187 (The Pile)

Max Activating Token Index: 800

Text #8

Max Range: 3.9488. Min Range: -3.9488

Max Act: 3.7549. Min Act: -0.0000

Data Index: 1951116 (The Pile)

Max Activating Token Index: 877

Text #9

Max Range: 3.9488. Min Range: -3.9488

Max Act: 3.5406. Min Act: -0.0000

Data Index: 333696 (The Pile)

Max Activating Token Index: 244

Text #10

Max Range: 3.9488. Min Range: -3.9488

Max Act: 3.3325. Min Act: -0.0000

Data Index: 1737299 (The Pile)

Max Activating Token Index: 378

Text #11

Max Range: 3.9488. Min Range: -3.9488

Max Act: 2.8654. Min Act: -0.0000

Data Index: 1729319 (The Pile)

Max Activating Token Index: 142

Text #12

Max Range: 3.9488. Min Range: -3.9488

Max Act: 3.3857. Min Act: -0.0000

Data Index: 125535 (The Pile)

Max Activating Token Index: 296

Text #13

Max Range: 3.9488. Min Range: -3.9488

Max Act: 3.2301. Min Act: -0.0000

Data Index: 1489015 (The Pile)

Max Activating Token Index: 308

Text #14

Max Range: 3.9488. Min Range: -3.9488

Max Act: 3.3886. Min Act: -0.0000

Data Index: 760054 (The Pile)

Max Activating Token Index: 631

Text #15

Max Range: 3.9488. Min Range: -3.9488

Max Act: 3.5874. Min Act: -0.0000

Data Index: 1913803 (The Pile)

Max Activating Token Index: 833

Text #16

Max Range: 3.9488. Min Range: -3.9488

Max Act: 2.6392. Min Act: -0.0000

Data Index: 1928129 (The Pile)

Max Activating Token Index: 894

Text #17

Max Range: 3.9488. Min Range: -3.9488

Max Act: 3.3268. Min Act: -0.0000

Data Index: 1508014 (The Pile)

Max Activating Token Index: 514

Text #18

Max Range: 3.9488. Min Range: -3.9488

Max Act: 3.2843. Min Act: -0.0000

Data Index: 1157514 (The Pile)

Max Activating Token Index: 877

Text #19

Max Range: 3.9488. Min Range: -3.9488

Max Act: 2.9727. Min Act: -0.0000

Data Index: 84813 (The Pile)

Max Activating Token Index: 794