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

Dataset: The Pile

Neuron 167 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6602. Min Range: -0.6602

Max Act: 0.6136. Min Act: -0.0000

Data Index: 1928243 (The Pile)

Max Activating Token Index: 223

Text #1

Max Range: 0.6602. Min Range: -0.6602

Max Act: 0.6602. Min Act: -0.0001

Data Index: 564911 (The Pile)

Max Activating Token Index: 699

Text #2

Max Range: 0.6602. Min Range: -0.6602

Max Act: 0.5752. Min Act: -0.0000

Data Index: 944294 (The Pile)

Max Activating Token Index: 251

Text #3

Max Range: 0.6602. Min Range: -0.6602

Max Act: 0.5881. Min Act: -0.0000

Data Index: 1805318 (The Pile)

Max Activating Token Index: 30

Text #4

Max Range: 0.6602. Min Range: -0.6602

Max Act: 0.5314. Min Act: -0.0000

Data Index: 1594642 (The Pile)

Max Activating Token Index: 210

Text #5

Max Range: 0.6602. Min Range: -0.6602

Max Act: 0.5610. Min Act: -0.0000

Data Index: 1999165 (The Pile)

Max Activating Token Index: 834

Text #6

Max Range: 0.6602. Min Range: -0.6602

Max Act: 0.5583. Min Act: -0.0000

Data Index: 1801940 (The Pile)

Max Activating Token Index: 498

Text #7

Max Range: 0.6602. Min Range: -0.6602

Max Act: 0.5293. Min Act: -0.0000

Data Index: 14929 (The Pile)

Max Activating Token Index: 608

Text #8

Max Range: 0.6602. Min Range: -0.6602

Max Act: 0.5456. Min Act: -0.0000

Data Index: 709701 (The Pile)

Max Activating Token Index: 365

Text #9

Max Range: 0.6602. Min Range: -0.6602

Max Act: 0.5961. Min Act: -0.0000

Data Index: 1972329 (The Pile)

Max Activating Token Index: 711

Text #10

Max Range: 0.6602. Min Range: -0.6602

Max Act: 0.5426. Min Act: -0.0000

Data Index: 226166 (The Pile)

Max Activating Token Index: 383

Text #11

Max Range: 0.6602. Min Range: -0.6602

Max Act: 0.5244. Min Act: -0.0000

Data Index: 1566677 (The Pile)

Max Activating Token Index: 645

Text #12

Max Range: 0.6602. Min Range: -0.6602

Max Act: 0.5036. Min Act: -0.0000

Data Index: 1881953 (The Pile)

Max Activating Token Index: 835

Text #13

Max Range: 0.6602. Min Range: -0.6602

Max Act: 0.5352. Min Act: -0.0000

Data Index: 1407273 (The Pile)

Max Activating Token Index: 102

Text #14

Max Range: 0.6602. Min Range: -0.6602

Max Act: 0.5327. Min Act: -0.0000

Data Index: 1699198 (The Pile)

Max Activating Token Index: 49

Text #15

Max Range: 0.6602. Min Range: -0.6602

Max Act: 0.5297. Min Act: -0.0000

Data Index: 337226 (The Pile)

Max Activating Token Index: 572

Text #16

Max Range: 0.6602. Min Range: -0.6602

Max Act: 0.5165. Min Act: -0.0000

Data Index: 64826 (The Pile)

Max Activating Token Index: 509

Text #17

Max Range: 0.6602. Min Range: -0.6602

Max Act: 0.5224. Min Act: -0.0000

Data Index: 37851 (The Pile)

Max Activating Token Index: 748

Text #18

Max Range: 0.6602. Min Range: -0.6602

Max Act: 0.5453. Min Act: -0.0000

Data Index: 1653398 (The Pile)

Max Activating Token Index: 1000

Text #19

Max Range: 0.6602. Min Range: -0.6602

Max Act: 0.4912. Min Act: -0.0000

Data Index: 980869 (The Pile)

Max Activating Token Index: 234