Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2721 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.5811. Min Range: -1.5811

Max Act: 1.5811. Min Act: -0.0000

Data Index: 1527458 (Python Code)

Max Activating Token Index: 803

Text #1

Max Range: 1.5811. Min Range: -1.5811

Max Act: 1.4038. Min Act: -0.0000

Data Index: 1433936 (Python Code)

Max Activating Token Index: 929

Text #2

Max Range: 1.5811. Min Range: -1.5811

Max Act: 1.3025. Min Act: -0.0000

Data Index: 1640456 (Python Code)

Max Activating Token Index: 385

Text #3

Max Range: 1.5811. Min Range: -1.5811

Max Act: 1.3331. Min Act: -0.0000

Data Index: 1565113 (Python Code)

Max Activating Token Index: 543

Text #4

Max Range: 1.5811. Min Range: -1.5811

Max Act: 1.1183. Min Act: -0.0000

Data Index: 1583271 (Python Code)

Max Activating Token Index: 844

Text #5

Max Range: 1.5811. Min Range: -1.5811

Max Act: 1.2029. Min Act: -0.0000

Data Index: 586188 (C4 (Web Text))

Max Activating Token Index: 154

Text #6

Max Range: 1.5811. Min Range: -1.5811

Max Act: 1.1954. Min Act: -0.0000

Data Index: 1595536 (Python Code)

Max Activating Token Index: 53

Text #7

Max Range: 1.5811. Min Range: -1.5811

Max Act: 1.1579. Min Act: -0.0000

Data Index: 571504 (C4 (Web Text))

Max Activating Token Index: 781

Text #8

Max Range: 1.5811. Min Range: -1.5811

Max Act: 1.1240. Min Act: -0.0000

Data Index: 1572702 (Python Code)

Max Activating Token Index: 870

Text #9

Max Range: 1.5811. Min Range: -1.5811

Max Act: 1.0844. Min Act: -0.0000

Data Index: 1572901 (Python Code)

Max Activating Token Index: 331

Text #10

Max Range: 1.5811. Min Range: -1.5811

Max Act: 1.0456. Min Act: -0.0000

Data Index: 825205 (C4 (Web Text))

Max Activating Token Index: 535

Text #11

Max Range: 1.5811. Min Range: -1.5811

Max Act: 0.9949. Min Act: -0.0000

Data Index: 439818 (C4 (Web Text))

Max Activating Token Index: 1010

Text #12

Max Range: 1.5811. Min Range: -1.5811

Max Act: 0.9103. Min Act: -0.0000

Data Index: 1497189 (Python Code)

Max Activating Token Index: 262

Text #13

Max Range: 1.5811. Min Range: -1.5811

Max Act: 1.0446. Min Act: -0.0000

Data Index: 1560319 (Python Code)

Max Activating Token Index: 697

Text #14

Max Range: 1.5811. Min Range: -1.5811

Max Act: 0.8988. Min Act: -0.0000

Data Index: 752404 (C4 (Web Text))

Max Activating Token Index: 329

Text #15

Max Range: 1.5811. Min Range: -1.5811

Max Act: 0.9375. Min Act: -0.0000

Data Index: 999520 (C4 (Web Text))

Max Activating Token Index: 599

Text #16

Max Range: 1.5811. Min Range: -1.5811

Max Act: 0.9791. Min Act: -0.0000

Data Index: 1406766 (Python Code)

Max Activating Token Index: 167

Text #17

Max Range: 1.5811. Min Range: -1.5811

Max Act: 0.9047. Min Act: -0.0000

Data Index: 363321 (C4 (Web Text))

Max Activating Token Index: 74

Text #18

Max Range: 1.5811. Min Range: -1.5811

Max Act: 0.8661. Min Act: -0.0000

Data Index: 526413 (C4 (Web Text))

Max Activating Token Index: 659

Text #19

Max Range: 1.5811. Min Range: -1.5811

Max Act: 0.8906. Min Act: -0.0000

Data Index: 118889 (C4 (Web Text))

Max Activating Token Index: 947