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

Dataset: The Pile

Neuron 4573 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: 1.3124. Min Range: -1.3124

Max Act: 1.3124. Min Act: -0.0000

Data Index: 954284 (The Pile)

Max Activating Token Index: 853

Text #1

Max Range: 1.3124. Min Range: -1.3124

Max Act: 0.9353. Min Act: -0.0000

Data Index: 1069311 (The Pile)

Max Activating Token Index: 747

Text #2

Max Range: 1.3124. Min Range: -1.3124

Max Act: 0.7963. Min Act: -0.0000

Data Index: 1730357 (The Pile)

Max Activating Token Index: 45

Text #3

Max Range: 1.3124. Min Range: -1.3124

Max Act: 0.7241. Min Act: -0.0000

Data Index: 52809 (The Pile)

Max Activating Token Index: 70

Text #4

Max Range: 1.3124. Min Range: -1.3124

Max Act: 0.8800. Min Act: -0.0000

Data Index: 1566793 (The Pile)

Max Activating Token Index: 62

Text #5

Max Range: 1.3124. Min Range: -1.3124

Max Act: 0.7371. Min Act: -0.0000

Data Index: 118386 (The Pile)

Max Activating Token Index: 196

Text #6

Max Range: 1.3124. Min Range: -1.3124

Max Act: 0.7043. Min Act: -0.0000

Data Index: 263047 (The Pile)

Max Activating Token Index: 450

Text #7

Max Range: 1.3124. Min Range: -1.3124

Max Act: 0.6546. Min Act: -0.0000

Data Index: 1397962 (The Pile)

Max Activating Token Index: 45

Text #8

Max Range: 1.3124. Min Range: -1.3124

Max Act: 0.7219. Min Act: -0.0000

Data Index: 870986 (The Pile)

Max Activating Token Index: 326

Text #9

Max Range: 1.3124. Min Range: -1.3124

Max Act: 0.6413. Min Act: -0.0000

Data Index: 466113 (The Pile)

Max Activating Token Index: 274

Text #10

Max Range: 1.3124. Min Range: -1.3124

Max Act: 0.6294. Min Act: -0.0000

Data Index: 1730638 (The Pile)

Max Activating Token Index: 404

Text #11

Max Range: 1.3124. Min Range: -1.3124

Max Act: 0.6375. Min Act: -0.0000

Data Index: 1671533 (The Pile)

Max Activating Token Index: 988

Text #12

Max Range: 1.3124. Min Range: -1.3124

Max Act: 0.5887. Min Act: -0.0000

Data Index: 1744182 (The Pile)

Max Activating Token Index: 427

Text #13

Max Range: 1.3124. Min Range: -1.3124

Max Act: 0.5420. Min Act: -0.0000

Data Index: 1748412 (The Pile)

Max Activating Token Index: 748

Text #14

Max Range: 1.3124. Min Range: -1.3124

Max Act: 0.5330. Min Act: -0.0000

Data Index: 461157 (The Pile)

Max Activating Token Index: 52

Text #15

Max Range: 1.3124. Min Range: -1.3124

Max Act: 0.5485. Min Act: -0.0000

Data Index: 1545436 (The Pile)

Max Activating Token Index: 137

Text #16

Max Range: 1.3124. Min Range: -1.3124

Max Act: 0.5366. Min Act: -0.0000

Data Index: 1548753 (The Pile)

Max Activating Token Index: 876

Text #17

Max Range: 1.3124. Min Range: -1.3124

Max Act: 0.5030. Min Act: -0.0000

Data Index: 1805132 (The Pile)

Max Activating Token Index: 700

Text #18

Max Range: 1.3124. Min Range: -1.3124

Max Act: 0.4742. Min Act: -0.0000

Data Index: 409550 (The Pile)

Max Activating Token Index: 280

Text #19

Max Range: 1.3124. Min Range: -1.3124

Max Act: 0.5189. Min Act: -0.0000

Data Index: 1867382 (The Pile)

Max Activating Token Index: 745