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

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

Neuron 2025 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.4822. Min Range: -3.4822

Max Act: 3.3725. Min Act: -0.0000

Data Index: 212052 (C4 (Web Text))

Max Activating Token Index: 640

Text #1

Max Range: 3.4822. Min Range: -3.4822

Max Act: 3.4452. Min Act: -0.0000

Data Index: 615163 (C4 (Web Text))

Max Activating Token Index: 679

Text #2

Max Range: 3.4822. Min Range: -3.4822

Max Act: 3.4822. Min Act: -0.0000

Data Index: 1047199 (C4 (Web Text))

Max Activating Token Index: 817

Text #3

Max Range: 3.4822. Min Range: -3.4822

Max Act: 3.2753. Min Act: -0.0000

Data Index: 409924 (C4 (Web Text))

Max Activating Token Index: 418

Text #4

Max Range: 3.4822. Min Range: -3.4822

Max Act: 3.2430. Min Act: -0.0000

Data Index: 717305 (C4 (Web Text))

Max Activating Token Index: 32

Text #5

Max Range: 3.4822. Min Range: -3.4822

Max Act: 3.2236. Min Act: -0.0001

Data Index: 886274 (C4 (Web Text))

Max Activating Token Index: 95

Text #6

Max Range: 3.4822. Min Range: -3.4822

Max Act: 3.2027. Min Act: -0.0000

Data Index: 908023 (C4 (Web Text))

Max Activating Token Index: 316

Text #7

Max Range: 3.4822. Min Range: -3.4822

Max Act: 3.2008. Min Act: -0.0000

Data Index: 1131793 (C4 (Web Text))

Max Activating Token Index: 621

Text #8

Max Range: 3.4822. Min Range: -3.4822

Max Act: 3.3544. Min Act: -0.0000

Data Index: 628004 (C4 (Web Text))

Max Activating Token Index: 1000

Text #9

Max Range: 3.4822. Min Range: -3.4822

Max Act: 2.8976. Min Act: -0.0000

Data Index: 67278 (C4 (Web Text))

Max Activating Token Index: 866

Text #10

Max Range: 3.4822. Min Range: -3.4822

Max Act: 2.8633. Min Act: -0.0000

Data Index: 1219489 (C4 (Web Text))

Max Activating Token Index: 80

Text #11

Max Range: 3.4822. Min Range: -3.4822

Max Act: 3.0057. Min Act: -0.0001

Data Index: 500167 (C4 (Web Text))

Max Activating Token Index: 414

Text #12

Max Range: 3.4822. Min Range: -3.4822

Max Act: 3.1269. Min Act: -0.0000

Data Index: 559416 (C4 (Web Text))

Max Activating Token Index: 173

Text #13

Max Range: 3.4822. Min Range: -3.4822

Max Act: 2.9800. Min Act: -0.0000

Data Index: 980998 (C4 (Web Text))

Max Activating Token Index: 207

Text #14

Max Range: 3.4822. Min Range: -3.4822

Max Act: 2.9758. Min Act: -0.0000

Data Index: 292691 (C4 (Web Text))

Max Activating Token Index: 298

Text #15

Max Range: 3.4822. Min Range: -3.4822

Max Act: 2.9611. Min Act: -0.0000

Data Index: 1068831 (C4 (Web Text))

Max Activating Token Index: 429

Text #16

Max Range: 3.4822. Min Range: -3.4822

Max Act: 3.0706. Min Act: -0.0000

Data Index: 750877 (C4 (Web Text))

Max Activating Token Index: 905

Text #17

Max Range: 3.4822. Min Range: -3.4822

Max Act: 2.9354. Min Act: -0.0000

Data Index: 333452 (C4 (Web Text))

Max Activating Token Index: 599

Text #18

Max Range: 3.4822. Min Range: -3.4822

Max Act: 2.9167. Min Act: -0.0000

Data Index: 518306 (C4 (Web Text))

Max Activating Token Index: 980

Text #19

Max Range: 3.4822. Min Range: -3.4822

Max Act: 2.8774. Min Act: -0.0000

Data Index: 1121463 (C4 (Web Text))

Max Activating Token Index: 503