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

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

Neuron 5450 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: 1.3280. Min Range: -1.3280

Max Act: 1.3280. Min Act: -0.0000

Data Index: 736591 (C4 (Web Text))

Max Activating Token Index: 807

Text #1

Max Range: 1.3280. Min Range: -1.3280

Max Act: 1.2117. Min Act: -0.0000

Data Index: 169691 (C4 (Web Text))

Max Activating Token Index: 228

Text #2

Max Range: 1.3280. Min Range: -1.3280

Max Act: 1.1661. Min Act: -0.0000

Data Index: 629671 (C4 (Web Text))

Max Activating Token Index: 876

Text #3

Max Range: 1.3280. Min Range: -1.3280

Max Act: 1.1962. Min Act: -0.0000

Data Index: 496889 (C4 (Web Text))

Max Activating Token Index: 426

Text #4

Max Range: 1.3280. Min Range: -1.3280

Max Act: 1.1858. Min Act: -0.0000

Data Index: 593266 (C4 (Web Text))

Max Activating Token Index: 294

Text #5

Max Range: 1.3280. Min Range: -1.3280

Max Act: 1.1717. Min Act: -0.0000

Data Index: 157603 (C4 (Web Text))

Max Activating Token Index: 219

Text #6

Max Range: 1.3280. Min Range: -1.3280

Max Act: 1.0653. Min Act: -0.0000

Data Index: 270427 (C4 (Web Text))

Max Activating Token Index: 937

Text #7

Max Range: 1.3280. Min Range: -1.3280

Max Act: 1.0594. Min Act: -0.0000

Data Index: 283118 (C4 (Web Text))

Max Activating Token Index: 910

Text #8

Max Range: 1.3280. Min Range: -1.3280

Max Act: 1.0613. Min Act: -0.0000

Data Index: 1108561 (C4 (Web Text))

Max Activating Token Index: 999

Text #9

Max Range: 1.3280. Min Range: -1.3280

Max Act: 1.0237. Min Act: -0.0000

Data Index: 545779 (C4 (Web Text))

Max Activating Token Index: 723

Text #10

Max Range: 1.3280. Min Range: -1.3280

Max Act: 1.0298. Min Act: -0.0000

Data Index: 68226 (C4 (Web Text))

Max Activating Token Index: 741

Text #11

Max Range: 1.3280. Min Range: -1.3280

Max Act: 0.9528. Min Act: -0.0000

Data Index: 86304 (C4 (Web Text))

Max Activating Token Index: 945

Text #12

Max Range: 1.3280. Min Range: -1.3280

Max Act: 0.9759. Min Act: -0.0000

Data Index: 680392 (C4 (Web Text))

Max Activating Token Index: 530

Text #13

Max Range: 1.3280. Min Range: -1.3280

Max Act: 1.0259. Min Act: -0.0000

Data Index: 235897 (C4 (Web Text))

Max Activating Token Index: 762

Text #14

Max Range: 1.3280. Min Range: -1.3280

Max Act: 1.0087. Min Act: -0.0000

Data Index: 1247834 (C4 (Web Text))

Max Activating Token Index: 901

Text #15

Max Range: 1.3280. Min Range: -1.3280

Max Act: 1.0018. Min Act: -0.0000

Data Index: 485873 (C4 (Web Text))

Max Activating Token Index: 387

Text #16

Max Range: 1.3280. Min Range: -1.3280

Max Act: 0.9898. Min Act: -0.0000

Data Index: 190426 (C4 (Web Text))

Max Activating Token Index: 125

Text #17

Max Range: 1.3280. Min Range: -1.3280

Max Act: 0.9874. Min Act: -0.0000

Data Index: 1190409 (C4 (Web Text))

Max Activating Token Index: 113

Text #18

Max Range: 1.3280. Min Range: -1.3280

Max Act: 0.9988. Min Act: -0.0000

Data Index: 482852 (C4 (Web Text))

Max Activating Token Index: 393

Text #19

Max Range: 1.3280. Min Range: -1.3280

Max Act: 0.9939. Min Act: -0.0000

Data Index: 1153134 (C4 (Web Text))

Max Activating Token Index: 106