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

Dataset: The Pile

Neuron 3978 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: 0.8157. Min Range: -0.8157

Max Act: 0.8157. Min Act: 0.0000

Data Index: 1631751 (The Pile)

Max Activating Token Index: 222

Text #1

Max Range: 0.8157. Min Range: -0.8157

Max Act: 0.6444. Min Act: -0.0000

Data Index: 184150 (The Pile)

Max Activating Token Index: 644

Text #2

Max Range: 0.8157. Min Range: -0.8157

Max Act: 0.5928. Min Act: -0.0000

Data Index: 1609920 (The Pile)

Max Activating Token Index: 36

Text #3

Max Range: 0.8157. Min Range: -0.8157

Max Act: 0.5617. Min Act: -0.0000

Data Index: 769383 (The Pile)

Max Activating Token Index: 84

Text #4

Max Range: 0.8157. Min Range: -0.8157

Max Act: 0.5629. Min Act: -0.0000

Data Index: 240864 (The Pile)

Max Activating Token Index: 243

Text #5

Max Range: 0.8157. Min Range: -0.8157

Max Act: 0.5592. Min Act: -0.0000

Data Index: 372431 (The Pile)

Max Activating Token Index: 22

Text #6

Max Range: 0.8157. Min Range: -0.8157

Max Act: 0.4864. Min Act: -0.0000

Data Index: 1974877 (The Pile)

Max Activating Token Index: 923

Text #7

Max Range: 0.8157. Min Range: -0.8157

Max Act: 0.4885. Min Act: -0.0000

Data Index: 1514923 (The Pile)

Max Activating Token Index: 536

Text #8

Max Range: 0.8157. Min Range: -0.8157

Max Act: 0.5184. Min Act: -0.0000

Data Index: 1877928 (The Pile)

Max Activating Token Index: 911

Text #9

Max Range: 0.8157. Min Range: -0.8157

Max Act: 0.4974. Min Act: -0.0000

Data Index: 250632 (The Pile)

Max Activating Token Index: 276

Text #10

Max Range: 0.8157. Min Range: -0.8157

Max Act: 0.4737. Min Act: -0.0000

Data Index: 939364 (The Pile)

Max Activating Token Index: 678

Text #11

Max Range: 0.8157. Min Range: -0.8157

Max Act: 0.4882. Min Act: -0.0000

Data Index: 1046152 (The Pile)

Max Activating Token Index: 409

Text #12

Max Range: 0.8157. Min Range: -0.8157

Max Act: 0.4888. Min Act: -0.0000

Data Index: 292155 (The Pile)

Max Activating Token Index: 62

Text #13

Max Range: 0.8157. Min Range: -0.8157

Max Act: 0.4804. Min Act: -0.0000

Data Index: 768917 (The Pile)

Max Activating Token Index: 1018

Text #14

Max Range: 0.8157. Min Range: -0.8157

Max Act: 0.4574. Min Act: -0.0000

Data Index: 1344040 (The Pile)

Max Activating Token Index: 505

Text #15

Max Range: 0.8157. Min Range: -0.8157

Max Act: 0.4604. Min Act: -0.0000

Data Index: 34596 (The Pile)

Max Activating Token Index: 803

Text #16

Max Range: 0.8157. Min Range: -0.8157

Max Act: 0.4415. Min Act: -0.0000

Data Index: 1084002 (The Pile)

Max Activating Token Index: 426

Text #17

Max Range: 0.8157. Min Range: -0.8157

Max Act: 0.4583. Min Act: -0.0000

Data Index: 341504 (The Pile)

Max Activating Token Index: 554

Text #18

Max Range: 0.8157. Min Range: -0.8157

Max Act: 0.4525. Min Act: -0.0000

Data Index: 1763415 (The Pile)

Max Activating Token Index: 220

Text #19

Max Range: 0.8157. Min Range: -0.8157

Max Act: 0.4314. Min Act: -0.0000

Data Index: 198015 (The Pile)

Max Activating Token Index: 63