Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 89 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.4583. Min Range: -1.4583

Max Act: 1.3585. Min Act: -0.0000

Data Index: 131777 (The Pile)

Max Activating Token Index: 1012

Text #1

Max Range: 1.4583. Min Range: -1.4583

Max Act: 1.4583. Min Act: -0.0000

Data Index: 820272 (The Pile)

Max Activating Token Index: 310

Text #2

Max Range: 1.4583. Min Range: -1.4583

Max Act: 1.1817. Min Act: -0.0000

Data Index: 503645 (The Pile)

Max Activating Token Index: 495

Text #3

Max Range: 1.4583. Min Range: -1.4583

Max Act: 1.2573. Min Act: -0.0000

Data Index: 969099 (The Pile)

Max Activating Token Index: 873

Text #4

Max Range: 1.4583. Min Range: -1.4583

Max Act: 1.1138. Min Act: -0.0000

Data Index: 1505964 (The Pile)

Max Activating Token Index: 87

Text #5

Max Range: 1.4583. Min Range: -1.4583

Max Act: 1.2054. Min Act: -0.0000

Data Index: 1739042 (The Pile)

Max Activating Token Index: 957

Text #6

Max Range: 1.4583. Min Range: -1.4583

Max Act: 1.1272. Min Act: -0.0000

Data Index: 621089 (The Pile)

Max Activating Token Index: 779

Text #7

Max Range: 1.4583. Min Range: -1.4583

Max Act: 1.2189. Min Act: -0.0000

Data Index: 351061 (The Pile)

Max Activating Token Index: 578

Text #8

Max Range: 1.4583. Min Range: -1.4583

Max Act: 1.2730. Min Act: -0.0000

Data Index: 1701007 (The Pile)

Max Activating Token Index: 53

Text #9

Max Range: 1.4583. Min Range: -1.4583

Max Act: 1.1416. Min Act: -0.0000

Data Index: 1511356 (The Pile)

Max Activating Token Index: 339

Text #10

Max Range: 1.4583. Min Range: -1.4583

Max Act: 1.0826. Min Act: -0.0000

Data Index: 1511827 (The Pile)

Max Activating Token Index: 680

Text #11

Max Range: 1.4583. Min Range: -1.4583

Max Act: 1.0996. Min Act: -0.0000

Data Index: 1128727 (The Pile)

Max Activating Token Index: 97

Text #12

Max Range: 1.4583. Min Range: -1.4583

Max Act: 1.0709. Min Act: -0.0000

Data Index: 1520753 (The Pile)

Max Activating Token Index: 369

Text #13

Max Range: 1.4583. Min Range: -1.4583

Max Act: 1.1302. Min Act: -0.0000

Data Index: 1358714 (The Pile)

Max Activating Token Index: 126

Text #14

Max Range: 1.4583. Min Range: -1.4583

Max Act: 1.0600. Min Act: -0.0000

Data Index: 13443 (The Pile)

Max Activating Token Index: 990

Text #15

Max Range: 1.4583. Min Range: -1.4583

Max Act: 1.0206. Min Act: -0.0000

Data Index: 595466 (The Pile)

Max Activating Token Index: 270

Text #16

Max Range: 1.4583. Min Range: -1.4583

Max Act: 1.0636. Min Act: -0.0000

Data Index: 1996463 (The Pile)

Max Activating Token Index: 169

Text #17

Max Range: 1.4583. Min Range: -1.4583

Max Act: 0.9712. Min Act: -0.0000

Data Index: 1154421 (The Pile)

Max Activating Token Index: 910

Text #18

Max Range: 1.4583. Min Range: -1.4583

Max Act: 1.0238. Min Act: -0.0000

Data Index: 509531 (The Pile)

Max Activating Token Index: 466

Text #19

Max Range: 1.4583. Min Range: -1.4583

Max Act: 0.9762. Min Act: -0.0000

Data Index: 184177 (The Pile)

Max Activating Token Index: 692