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

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

Neuron 5117 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: 2.5838. Min Range: -2.5838

Max Act: 2.5838. Min Act: -0.0000

Data Index: 291887 (C4 (Web Text))

Max Activating Token Index: 374

Text #1

Max Range: 2.5838. Min Range: -2.5838

Max Act: 2.3114. Min Act: -0.0000

Data Index: 1523641 (Python Code)

Max Activating Token Index: 764

Text #2

Max Range: 2.5838. Min Range: -2.5838

Max Act: 2.2911. Min Act: -0.0000

Data Index: 1425910 (Python Code)

Max Activating Token Index: 267

Text #3

Max Range: 2.5838. Min Range: -2.5838

Max Act: 2.1540. Min Act: -0.0000

Data Index: 1470599 (Python Code)

Max Activating Token Index: 697

Text #4

Max Range: 2.5838. Min Range: -2.5838

Max Act: 2.2483. Min Act: -0.0000

Data Index: 1451475 (Python Code)

Max Activating Token Index: 509

Text #5

Max Range: 2.5838. Min Range: -2.5838

Max Act: 2.3545. Min Act: -0.0000

Data Index: 313988 (C4 (Web Text))

Max Activating Token Index: 1003

Text #6

Max Range: 2.5838. Min Range: -2.5838

Max Act: 2.0872. Min Act: -0.0000

Data Index: 234267 (C4 (Web Text))

Max Activating Token Index: 943

Text #7

Max Range: 2.5838. Min Range: -2.5838

Max Act: 2.2889. Min Act: -0.0000

Data Index: 1437384 (Python Code)

Max Activating Token Index: 834

Text #8

Max Range: 2.5838. Min Range: -2.5838

Max Act: 2.1680. Min Act: -0.0000

Data Index: 1518631 (Python Code)

Max Activating Token Index: 996

Text #9

Max Range: 2.5838. Min Range: -2.5838

Max Act: 2.0085. Min Act: 0.0000

Data Index: 1470528 (Python Code)

Max Activating Token Index: 179

Text #10

Max Range: 2.5838. Min Range: -2.5838

Max Act: 2.0678. Min Act: -0.0000

Data Index: 1528265 (Python Code)

Max Activating Token Index: 793

Text #11

Max Range: 2.5838. Min Range: -2.5838

Max Act: 1.9646. Min Act: -0.0000

Data Index: 1418007 (Python Code)

Max Activating Token Index: 1022

Text #12

Max Range: 2.5838. Min Range: -2.5838

Max Act: 2.0513. Min Act: -0.0000

Data Index: 734941 (C4 (Web Text))

Max Activating Token Index: 646

Text #13

Max Range: 2.5838. Min Range: -2.5838

Max Act: 1.9162. Min Act: -0.0000

Data Index: 1165514 (C4 (Web Text))

Max Activating Token Index: 948

Text #14

Max Range: 2.5838. Min Range: -2.5838

Max Act: 1.8808. Min Act: -0.0000

Data Index: 1407669 (Python Code)

Max Activating Token Index: 248

Text #15

Max Range: 2.5838. Min Range: -2.5838

Max Act: 1.8719. Min Act: -0.0000

Data Index: 1477700 (Python Code)

Max Activating Token Index: 324

Text #16

Max Range: 2.5838. Min Range: -2.5838

Max Act: 1.7551. Min Act: -0.0000

Data Index: 383667 (C4 (Web Text))

Max Activating Token Index: 191

Text #17

Max Range: 2.5838. Min Range: -2.5838

Max Act: 1.8308. Min Act: -0.0000

Data Index: 1534272 (Python Code)

Max Activating Token Index: 546

Text #18

Max Range: 2.5838. Min Range: -2.5838

Max Act: 1.8155. Min Act: -0.0000

Data Index: 1618065 (Python Code)

Max Activating Token Index: 495

Text #19

Max Range: 2.5838. Min Range: -2.5838

Max Act: 1.8244. Min Act: -0.0000

Data Index: 300507 (C4 (Web Text))

Max Activating Token Index: 174