Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3860 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.2707. Min Range: -1.2707

Max Act: 1.2707. Min Act: -0.0001

Data Index: 945104 (C4 (Web Text))

Max Activating Token Index: 459

Text #1

Max Range: 1.2707. Min Range: -1.2707

Max Act: 1.0609. Min Act: -0.0001

Data Index: 825830 (C4 (Web Text))

Max Activating Token Index: 365

Text #2

Max Range: 1.2707. Min Range: -1.2707

Max Act: 1.0113. Min Act: -0.0001

Data Index: 607602 (C4 (Web Text))

Max Activating Token Index: 629

Text #3

Max Range: 1.2707. Min Range: -1.2707

Max Act: 0.9719. Min Act: -0.0001

Data Index: 681390 (C4 (Web Text))

Max Activating Token Index: 798

Text #4

Max Range: 1.2707. Min Range: -1.2707

Max Act: 0.9375. Min Act: -0.0001

Data Index: 582877 (C4 (Web Text))

Max Activating Token Index: 770

Text #5

Max Range: 1.2707. Min Range: -1.2707

Max Act: 0.9888. Min Act: -0.0001

Data Index: 172202 (C4 (Web Text))

Max Activating Token Index: 131

Text #6

Max Range: 1.2707. Min Range: -1.2707

Max Act: 0.9146. Min Act: -0.0001

Data Index: 381702 (C4 (Web Text))

Max Activating Token Index: 143

Text #7

Max Range: 1.2707. Min Range: -1.2707

Max Act: 0.9325. Min Act: -0.0001

Data Index: 1213980 (C4 (Web Text))

Max Activating Token Index: 423

Text #8

Max Range: 1.2707. Min Range: -1.2707

Max Act: 0.8851. Min Act: -0.0001

Data Index: 523956 (C4 (Web Text))

Max Activating Token Index: 553

Text #9

Max Range: 1.2707. Min Range: -1.2707

Max Act: 0.8623. Min Act: -0.0001

Data Index: 1540079 (Python Code)

Max Activating Token Index: 356

Text #10

Max Range: 1.2707. Min Range: -1.2707

Max Act: 0.8861. Min Act: -0.0001

Data Index: 23184 (C4 (Web Text))

Max Activating Token Index: 634

Text #11

Max Range: 1.2707. Min Range: -1.2707

Max Act: 0.9070. Min Act: -0.0001

Data Index: 510644 (C4 (Web Text))

Max Activating Token Index: 74

Text #12

Max Range: 1.2707. Min Range: -1.2707

Max Act: 0.8756. Min Act: -0.0001

Data Index: 1327059 (C4 (Web Text))

Max Activating Token Index: 351

Text #13

Max Range: 1.2707. Min Range: -1.2707

Max Act: 0.8640. Min Act: -0.0001

Data Index: 660491 (C4 (Web Text))

Max Activating Token Index: 113

Text #14

Max Range: 1.2707. Min Range: -1.2707

Max Act: 0.8816. Min Act: -0.0001

Data Index: 1310601 (C4 (Web Text))

Max Activating Token Index: 674

Text #15

Max Range: 1.2707. Min Range: -1.2707

Max Act: 0.8550. Min Act: -0.0001

Data Index: 1132706 (C4 (Web Text))

Max Activating Token Index: 108

Text #16

Max Range: 1.2707. Min Range: -1.2707

Max Act: 0.8559. Min Act: -0.0001

Data Index: 826526 (C4 (Web Text))

Max Activating Token Index: 557

Text #17

Max Range: 1.2707. Min Range: -1.2707

Max Act: 0.8785. Min Act: -0.0001

Data Index: 296536 (C4 (Web Text))

Max Activating Token Index: 167

Text #18

Max Range: 1.2707. Min Range: -1.2707

Max Act: 0.8473. Min Act: -0.0001

Data Index: 75284 (C4 (Web Text))

Max Activating Token Index: 10

Text #19

Max Range: 1.2707. Min Range: -1.2707

Max Act: 0.8069. Min Act: -0.0001

Data Index: 973799 (C4 (Web Text))

Max Activating Token Index: 177