Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1468 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.1585. Min Range: -2.1585

Max Act: 2.1585. Min Act: -0.0000

Data Index: 1336276 (C4 (Web Text))

Max Activating Token Index: 603

Text #1

Max Range: 2.1585. Min Range: -2.1585

Max Act: 2.0643. Min Act: -0.0000

Data Index: 196355 (C4 (Web Text))

Max Activating Token Index: 545

Text #2

Max Range: 2.1585. Min Range: -2.1585

Max Act: 2.0626. Min Act: -0.0000

Data Index: 890181 (C4 (Web Text))

Max Activating Token Index: 991

Text #3

Max Range: 2.1585. Min Range: -2.1585

Max Act: 1.9211. Min Act: -0.0000

Data Index: 287921 (C4 (Web Text))

Max Activating Token Index: 573

Text #4

Max Range: 2.1585. Min Range: -2.1585

Max Act: 1.7061. Min Act: -0.0000

Data Index: 517912 (C4 (Web Text))

Max Activating Token Index: 139

Text #5

Max Range: 2.1585. Min Range: -2.1585

Max Act: 1.7041. Min Act: -0.0000

Data Index: 488720 (C4 (Web Text))

Max Activating Token Index: 951

Text #6

Max Range: 2.1585. Min Range: -2.1585

Max Act: 1.6691. Min Act: -0.0000

Data Index: 179448 (C4 (Web Text))

Max Activating Token Index: 507

Text #7

Max Range: 2.1585. Min Range: -2.1585

Max Act: 1.5504. Min Act: -0.0000

Data Index: 493101 (C4 (Web Text))

Max Activating Token Index: 449

Text #8

Max Range: 2.1585. Min Range: -2.1585

Max Act: 1.6346. Min Act: -0.0000

Data Index: 305797 (C4 (Web Text))

Max Activating Token Index: 135

Text #9

Max Range: 2.1585. Min Range: -2.1585

Max Act: 1.5769. Min Act: -0.0000

Data Index: 816214 (C4 (Web Text))

Max Activating Token Index: 284

Text #10

Max Range: 2.1585. Min Range: -2.1585

Max Act: 1.5691. Min Act: -0.0000

Data Index: 31858 (C4 (Web Text))

Max Activating Token Index: 729

Text #11

Max Range: 2.1585. Min Range: -2.1585

Max Act: 1.5618. Min Act: -0.0000

Data Index: 1242101 (C4 (Web Text))

Max Activating Token Index: 158

Text #12

Max Range: 2.1585. Min Range: -2.1585

Max Act: 1.4566. Min Act: -0.0000

Data Index: 1060119 (C4 (Web Text))

Max Activating Token Index: 4

Text #13

Max Range: 2.1585. Min Range: -2.1585

Max Act: 1.5281. Min Act: -0.0000

Data Index: 186674 (C4 (Web Text))

Max Activating Token Index: 388

Text #14

Max Range: 2.1585. Min Range: -2.1585

Max Act: 1.5295. Min Act: -0.0000

Data Index: 460268 (C4 (Web Text))

Max Activating Token Index: 508

Text #15

Max Range: 2.1585. Min Range: -2.1585

Max Act: 1.5255. Min Act: -0.0000

Data Index: 798060 (C4 (Web Text))

Max Activating Token Index: 489

Text #16

Max Range: 2.1585. Min Range: -2.1585

Max Act: 1.6075. Min Act: -0.0000

Data Index: 669174 (C4 (Web Text))

Max Activating Token Index: 595

Text #17

Max Range: 2.1585. Min Range: -2.1585

Max Act: 1.5178. Min Act: -0.0000

Data Index: 1097934 (C4 (Web Text))

Max Activating Token Index: 1008

Text #18

Max Range: 2.1585. Min Range: -2.1585

Max Act: 1.5182. Min Act: -0.0000

Data Index: 1070582 (C4 (Web Text))

Max Activating Token Index: 952

Text #19

Max Range: 2.1585. Min Range: -2.1585

Max Act: 1.5223. Min Act: -0.0000

Data Index: 805075 (C4 (Web Text))

Max Activating Token Index: 280