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

Dataset: The Pile

Neuron 4540 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: 3.1186. Min Range: -3.1186

Max Act: 3.1186. Min Act: -0.0000

Data Index: 768630 (The Pile)

Max Activating Token Index: 1021

Text #1

Max Range: 3.1186. Min Range: -3.1186

Max Act: 2.9486. Min Act: -0.0000

Data Index: 1379618 (The Pile)

Max Activating Token Index: 340

Text #2

Max Range: 3.1186. Min Range: -3.1186

Max Act: 2.6857. Min Act: -0.0000

Data Index: 1408563 (The Pile)

Max Activating Token Index: 251

Text #3

Max Range: 3.1186. Min Range: -3.1186

Max Act: 2.8370. Min Act: -0.0000

Data Index: 63677 (The Pile)

Max Activating Token Index: 372

Text #4

Max Range: 3.1186. Min Range: -3.1186

Max Act: 2.7893. Min Act: -0.0000

Data Index: 36341 (The Pile)

Max Activating Token Index: 876

Text #5

Max Range: 3.1186. Min Range: -3.1186

Max Act: 2.9284. Min Act: -0.0000

Data Index: 450849 (The Pile)

Max Activating Token Index: 249

Text #6

Max Range: 3.1186. Min Range: -3.1186

Max Act: 2.6745. Min Act: -0.0000

Data Index: 169420 (The Pile)

Max Activating Token Index: 927

Text #7

Max Range: 3.1186. Min Range: -3.1186

Max Act: 2.5673. Min Act: -0.0000

Data Index: 129358 (The Pile)

Max Activating Token Index: 259

Text #8

Max Range: 3.1186. Min Range: -3.1186

Max Act: 2.5135. Min Act: -0.0000

Data Index: 94612 (The Pile)

Max Activating Token Index: 541

Text #9

Max Range: 3.1186. Min Range: -3.1186

Max Act: 2.6530. Min Act: -0.0000

Data Index: 1686645 (The Pile)

Max Activating Token Index: 653

Text #10

Max Range: 3.1186. Min Range: -3.1186

Max Act: 2.4465. Min Act: -0.0000

Data Index: 547152 (The Pile)

Max Activating Token Index: 877

Text #11

Max Range: 3.1186. Min Range: -3.1186

Max Act: 2.5632. Min Act: -0.0000

Data Index: 34525 (The Pile)

Max Activating Token Index: 41

Text #12

Max Range: 3.1186. Min Range: -3.1186

Max Act: 2.1734. Min Act: -0.0000

Data Index: 1612265 (The Pile)

Max Activating Token Index: 591

Text #13

Max Range: 3.1186. Min Range: -3.1186

Max Act: 2.2786. Min Act: -0.0000

Data Index: 1328817 (The Pile)

Max Activating Token Index: 805

Text #14

Max Range: 3.1186. Min Range: -3.1186

Max Act: 2.6754. Min Act: -0.0000

Data Index: 1048070 (The Pile)

Max Activating Token Index: 210

Text #15

Max Range: 3.1186. Min Range: -3.1186

Max Act: 2.6718. Min Act: -0.0000

Data Index: 937312 (The Pile)

Max Activating Token Index: 157

Text #16

Max Range: 3.1186. Min Range: -3.1186

Max Act: 2.4169. Min Act: -0.0000

Data Index: 1229789 (The Pile)

Max Activating Token Index: 392

Text #17

Max Range: 3.1186. Min Range: -3.1186

Max Act: 2.5245. Min Act: -0.0000

Data Index: 1863763 (The Pile)

Max Activating Token Index: 214

Text #18

Max Range: 3.1186. Min Range: -3.1186

Max Act: 2.5002. Min Act: -0.0000

Data Index: 108181 (The Pile)

Max Activating Token Index: 407

Text #19

Max Range: 3.1186. Min Range: -3.1186

Max Act: 2.4789. Min Act: -0.0000

Data Index: 666175 (The Pile)

Max Activating Token Index: 319