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

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

Neuron 986 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8549. Min Range: -0.8549

Max Act: 0.8549. Min Act: -0.0000

Data Index: 1053550 (C4 (Web Text))

Max Activating Token Index: 190

Text #1

Max Range: 0.8549. Min Range: -0.8549

Max Act: 0.7672. Min Act: -0.0000

Data Index: 220940 (C4 (Web Text))

Max Activating Token Index: 340

Text #2

Max Range: 0.8549. Min Range: -0.8549

Max Act: 0.6572. Min Act: -0.0000

Data Index: 6119 (C4 (Web Text))

Max Activating Token Index: 101

Text #3

Max Range: 0.8549. Min Range: -0.8549

Max Act: 0.5684. Min Act: -0.0000

Data Index: 1402769 (Python Code)

Max Activating Token Index: 310

Text #4

Max Range: 0.8549. Min Range: -0.8549

Max Act: 0.6002. Min Act: -0.0000

Data Index: 1379542 (Python Code)

Max Activating Token Index: 261

Text #5

Max Range: 0.8549. Min Range: -0.8549

Max Act: 0.6146. Min Act: -0.0000

Data Index: 952848 (C4 (Web Text))

Max Activating Token Index: 567

Text #6

Max Range: 0.8549. Min Range: -0.8549

Max Act: 0.6023. Min Act: -0.0000

Data Index: 364230 (C4 (Web Text))

Max Activating Token Index: 90

Text #7

Max Range: 0.8549. Min Range: -0.8549

Max Act: 0.5615. Min Act: -0.0000

Data Index: 392046 (C4 (Web Text))

Max Activating Token Index: 434

Text #8

Max Range: 0.8549. Min Range: -0.8549

Max Act: 0.6079. Min Act: -0.0000

Data Index: 1653196 (Python Code)

Max Activating Token Index: 291

Text #9

Max Range: 0.8549. Min Range: -0.8549

Max Act: 0.6302. Min Act: -0.0000

Data Index: 50672 (C4 (Web Text))

Max Activating Token Index: 97

Text #10

Max Range: 0.8549. Min Range: -0.8549

Max Act: 0.5515. Min Act: -0.0000

Data Index: 455339 (C4 (Web Text))

Max Activating Token Index: 995

Text #11

Max Range: 0.8549. Min Range: -0.8549

Max Act: 0.5106. Min Act: -0.0000

Data Index: 1279814 (C4 (Web Text))

Max Activating Token Index: 683

Text #12

Max Range: 0.8549. Min Range: -0.8549

Max Act: 0.5562. Min Act: -0.0000

Data Index: 460379 (C4 (Web Text))

Max Activating Token Index: 972

Text #13

Max Range: 0.8549. Min Range: -0.8549

Max Act: 0.5428. Min Act: -0.0000

Data Index: 1012944 (C4 (Web Text))

Max Activating Token Index: 201

Text #14

Max Range: 0.8549. Min Range: -0.8549

Max Act: 0.5597. Min Act: -0.0000

Data Index: 308372 (C4 (Web Text))

Max Activating Token Index: 91

Text #15

Max Range: 0.8549. Min Range: -0.8549

Max Act: 0.5595. Min Act: -0.0000

Data Index: 1393780 (Python Code)

Max Activating Token Index: 837

Text #16

Max Range: 0.8549. Min Range: -0.8549

Max Act: 0.5902. Min Act: -0.0000

Data Index: 149503 (C4 (Web Text))

Max Activating Token Index: 126

Text #17

Max Range: 0.8549. Min Range: -0.8549

Max Act: 0.5433. Min Act: -0.0000

Data Index: 227853 (C4 (Web Text))

Max Activating Token Index: 291

Text #18

Max Range: 0.8549. Min Range: -0.8549

Max Act: 0.5561. Min Act: -0.0000

Data Index: 780165 (C4 (Web Text))

Max Activating Token Index: 854

Text #19

Max Range: 0.8549. Min Range: -0.8549

Max Act: 0.5723. Min Act: -0.0000

Data Index: 1587409 (Python Code)

Max Activating Token Index: 351