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

Dataset: The Pile

Neuron 4538 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1219. Min Range: -1.1219

Max Act: 1.1219. Min Act: -0.0000

Data Index: 273641 (The Pile)

Max Activating Token Index: 801

Text #1

Max Range: 1.1219. Min Range: -1.1219

Max Act: 0.9925. Min Act: -0.0000

Data Index: 704863 (The Pile)

Max Activating Token Index: 651

Text #2

Max Range: 1.1219. Min Range: -1.1219

Max Act: 0.9873. Min Act: -0.0000

Data Index: 455117 (The Pile)

Max Activating Token Index: 333

Text #3

Max Range: 1.1219. Min Range: -1.1219

Max Act: 0.9198. Min Act: -0.0000

Data Index: 1935126 (The Pile)

Max Activating Token Index: 20

Text #4

Max Range: 1.1219. Min Range: -1.1219

Max Act: 0.9541. Min Act: -0.0000

Data Index: 1449078 (The Pile)

Max Activating Token Index: 1019

Text #5

Max Range: 1.1219. Min Range: -1.1219

Max Act: 0.8682. Min Act: -0.0000

Data Index: 419916 (The Pile)

Max Activating Token Index: 450

Text #6

Max Range: 1.1219. Min Range: -1.1219

Max Act: 0.8722. Min Act: -0.0000

Data Index: 1544316 (The Pile)

Max Activating Token Index: 205

Text #7

Max Range: 1.1219. Min Range: -1.1219

Max Act: 0.9078. Min Act: -0.0000

Data Index: 245662 (The Pile)

Max Activating Token Index: 75

Text #8

Max Range: 1.1219. Min Range: -1.1219

Max Act: 0.7876. Min Act: -0.0000

Data Index: 1843384 (The Pile)

Max Activating Token Index: 802

Text #9

Max Range: 1.1219. Min Range: -1.1219

Max Act: 0.8498. Min Act: -0.0000

Data Index: 818764 (The Pile)

Max Activating Token Index: 378

Text #10

Max Range: 1.1219. Min Range: -1.1219

Max Act: 0.8156. Min Act: -0.0000

Data Index: 1790026 (The Pile)

Max Activating Token Index: 460

Text #11

Max Range: 1.1219. Min Range: -1.1219

Max Act: 0.8534. Min Act: -0.0000

Data Index: 887720 (The Pile)

Max Activating Token Index: 296

Text #12

Max Range: 1.1219. Min Range: -1.1219

Max Act: 0.8514. Min Act: -0.0000

Data Index: 1976876 (The Pile)

Max Activating Token Index: 210

Text #13

Max Range: 1.1219. Min Range: -1.1219

Max Act: 0.9004. Min Act: -0.0000

Data Index: 1662711 (The Pile)

Max Activating Token Index: 668

Text #14

Max Range: 1.1219. Min Range: -1.1219

Max Act: 0.9280. Min Act: -0.0000

Data Index: 1847176 (The Pile)

Max Activating Token Index: 636

Text #15

Max Range: 1.1219. Min Range: -1.1219

Max Act: 0.8125. Min Act: -0.0000

Data Index: 1086496 (The Pile)

Max Activating Token Index: 934

Text #16

Max Range: 1.1219. Min Range: -1.1219

Max Act: 0.8088. Min Act: -0.0000

Data Index: 1294605 (The Pile)

Max Activating Token Index: 319

Text #17

Max Range: 1.1219. Min Range: -1.1219

Max Act: 0.8263. Min Act: -0.0000

Data Index: 429953 (The Pile)

Max Activating Token Index: 776

Text #18

Max Range: 1.1219. Min Range: -1.1219

Max Act: 0.7784. Min Act: -0.0000

Data Index: 986718 (The Pile)

Max Activating Token Index: 844

Text #19

Max Range: 1.1219. Min Range: -1.1219

Max Act: 0.7663. Min Act: -0.0000

Data Index: 1204672 (The Pile)

Max Activating Token Index: 842