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

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

Neuron 3052 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: 1.8672. Min Range: -1.8672

Max Act: 1.8672. Min Act: 0.0000

Data Index: 353764 (C4 (Web Text))

Max Activating Token Index: 645

Text #1

Max Range: 1.8672. Min Range: -1.8672

Max Act: 1.3596. Min Act: -0.0000

Data Index: 671786 (C4 (Web Text))

Max Activating Token Index: 857

Text #2

Max Range: 1.8672. Min Range: -1.8672

Max Act: 1.4877. Min Act: -0.0000

Data Index: 653975 (C4 (Web Text))

Max Activating Token Index: 730

Text #3

Max Range: 1.8672. Min Range: -1.8672

Max Act: 1.3016. Min Act: -0.0000

Data Index: 783417 (C4 (Web Text))

Max Activating Token Index: 450

Text #4

Max Range: 1.8672. Min Range: -1.8672

Max Act: 1.2161. Min Act: -0.0000

Data Index: 550097 (C4 (Web Text))

Max Activating Token Index: 643

Text #5

Max Range: 1.8672. Min Range: -1.8672

Max Act: 1.2467. Min Act: -0.0000

Data Index: 722304 (C4 (Web Text))

Max Activating Token Index: 731

Text #6

Max Range: 1.8672. Min Range: -1.8672

Max Act: 1.2036. Min Act: -0.0000

Data Index: 802812 (C4 (Web Text))

Max Activating Token Index: 506

Text #7

Max Range: 1.8672. Min Range: -1.8672

Max Act: 1.1996. Min Act: -0.0000

Data Index: 463482 (C4 (Web Text))

Max Activating Token Index: 544

Text #8

Max Range: 1.8672. Min Range: -1.8672

Max Act: 1.1725. Min Act: -0.0000

Data Index: 454428 (C4 (Web Text))

Max Activating Token Index: 356

Text #9

Max Range: 1.8672. Min Range: -1.8672

Max Act: 1.1441. Min Act: -0.0000

Data Index: 1074033 (C4 (Web Text))

Max Activating Token Index: 706

Text #10

Max Range: 1.8672. Min Range: -1.8672

Max Act: 1.0937. Min Act: -0.0000

Data Index: 373296 (C4 (Web Text))

Max Activating Token Index: 935

Text #11

Max Range: 1.8672. Min Range: -1.8672

Max Act: 1.0813. Min Act: -0.0000

Data Index: 354736 (C4 (Web Text))

Max Activating Token Index: 288

Text #12

Max Range: 1.8672. Min Range: -1.8672

Max Act: 1.0659. Min Act: -0.0000

Data Index: 636782 (C4 (Web Text))

Max Activating Token Index: 663

Text #13

Max Range: 1.8672. Min Range: -1.8672

Max Act: 1.0651. Min Act: -0.0000

Data Index: 207285 (C4 (Web Text))

Max Activating Token Index: 490

Text #14

Max Range: 1.8672. Min Range: -1.8672

Max Act: 1.1224. Min Act: -0.0000

Data Index: 100209 (C4 (Web Text))

Max Activating Token Index: 640

Text #15

Max Range: 1.8672. Min Range: -1.8672

Max Act: 1.1132. Min Act: -0.0000

Data Index: 356819 (C4 (Web Text))

Max Activating Token Index: 211

Text #16

Max Range: 1.8672. Min Range: -1.8672

Max Act: 1.0351. Min Act: -0.0000

Data Index: 388411 (C4 (Web Text))

Max Activating Token Index: 826

Text #17

Max Range: 1.8672. Min Range: -1.8672

Max Act: 1.0426. Min Act: -0.0000

Data Index: 146886 (C4 (Web Text))

Max Activating Token Index: 35

Text #18

Max Range: 1.8672. Min Range: -1.8672

Max Act: 1.0166. Min Act: -0.0000

Data Index: 225086 (C4 (Web Text))

Max Activating Token Index: 309

Text #19

Max Range: 1.8672. Min Range: -1.8672

Max Act: 1.0294. Min Act: -0.0000

Data Index: 681880 (C4 (Web Text))

Max Activating Token Index: 689