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

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

Neuron 382 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: 1.2899. Min Range: -1.2899

Max Act: 1.2659. Min Act: -0.0000

Data Index: 676096 (C4 (Web Text))

Max Activating Token Index: 797

Text #1

Max Range: 1.2899. Min Range: -1.2899

Max Act: 1.2294. Min Act: -0.0000

Data Index: 1502248 (Python Code)

Max Activating Token Index: 794

Text #2

Max Range: 1.2899. Min Range: -1.2899

Max Act: 1.2805. Min Act: -0.0000

Data Index: 1546795 (Python Code)

Max Activating Token Index: 200

Text #3

Max Range: 1.2899. Min Range: -1.2899

Max Act: 1.2305. Min Act: -0.0000

Data Index: 1382356 (Python Code)

Max Activating Token Index: 308

Text #4

Max Range: 1.2899. Min Range: -1.2899

Max Act: 1.2899. Min Act: -0.0000

Data Index: 1636262 (Python Code)

Max Activating Token Index: 186

Text #5

Max Range: 1.2899. Min Range: -1.2899

Max Act: 1.1698. Min Act: -0.0000

Data Index: 1048760 (C4 (Web Text))

Max Activating Token Index: 277

Text #6

Max Range: 1.2899. Min Range: -1.2899

Max Act: 1.1759. Min Act: -0.0000

Data Index: 1636198 (Python Code)

Max Activating Token Index: 242

Text #7

Max Range: 1.2899. Min Range: -1.2899

Max Act: 1.2091. Min Act: -0.0000

Data Index: 416969 (C4 (Web Text))

Max Activating Token Index: 133

Text #8

Max Range: 1.2899. Min Range: -1.2899

Max Act: 1.1898. Min Act: -0.0000

Data Index: 378784 (C4 (Web Text))

Max Activating Token Index: 419

Text #9

Max Range: 1.2899. Min Range: -1.2899

Max Act: 1.1967. Min Act: -0.0000

Data Index: 1454433 (Python Code)

Max Activating Token Index: 392

Text #10

Max Range: 1.2899. Min Range: -1.2899

Max Act: 1.0934. Min Act: -0.0000

Data Index: 1243756 (C4 (Web Text))

Max Activating Token Index: 312

Text #11

Max Range: 1.2899. Min Range: -1.2899

Max Act: 1.1196. Min Act: -0.0000

Data Index: 1436473 (Python Code)

Max Activating Token Index: 444

Text #12

Max Range: 1.2899. Min Range: -1.2899

Max Act: 1.0961. Min Act: -0.0000

Data Index: 1369168 (Python Code)

Max Activating Token Index: 119

Text #13

Max Range: 1.2899. Min Range: -1.2899

Max Act: 1.1036. Min Act: -0.0000

Data Index: 1531648 (Python Code)

Max Activating Token Index: 89

Text #14

Max Range: 1.2899. Min Range: -1.2899

Max Act: 1.1282. Min Act: -0.0000

Data Index: 250435 (C4 (Web Text))

Max Activating Token Index: 709

Text #15

Max Range: 1.2899. Min Range: -1.2899

Max Act: 1.0517. Min Act: -0.0000

Data Index: 1415655 (Python Code)

Max Activating Token Index: 886

Text #16

Max Range: 1.2899. Min Range: -1.2899

Max Act: 1.0109. Min Act: -0.0000

Data Index: 691163 (C4 (Web Text))

Max Activating Token Index: 101

Text #17

Max Range: 1.2899. Min Range: -1.2899

Max Act: 1.0513. Min Act: -0.0000

Data Index: 1634551 (Python Code)

Max Activating Token Index: 850

Text #18

Max Range: 1.2899. Min Range: -1.2899

Max Act: 1.1437. Min Act: -0.0000

Data Index: 1507988 (Python Code)

Max Activating Token Index: 434

Text #19

Max Range: 1.2899. Min Range: -1.2899

Max Act: 1.0315. Min Act: -0.0000

Data Index: 1369153 (Python Code)

Max Activating Token Index: 747