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

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

Neuron 991 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1886. Min Range: -3.1886

Max Act: 3.1886. Min Act: -0.0000

Data Index: 383833 (C4 (Web Text))

Max Activating Token Index: 230

Text #1

Max Range: 3.1886. Min Range: -3.1886

Max Act: 2.4163. Min Act: -0.0000

Data Index: 684726 (C4 (Web Text))

Max Activating Token Index: 895

Text #2

Max Range: 3.1886. Min Range: -3.1886

Max Act: 1.6896. Min Act: -0.0000

Data Index: 154573 (C4 (Web Text))

Max Activating Token Index: 40

Text #3

Max Range: 3.1886. Min Range: -3.1886

Max Act: 1.7367. Min Act: -0.0000

Data Index: 767662 (C4 (Web Text))

Max Activating Token Index: 558

Text #4

Max Range: 3.1886. Min Range: -3.1886

Max Act: 1.7311. Min Act: -0.0000

Data Index: 59266 (C4 (Web Text))

Max Activating Token Index: 768

Text #5

Max Range: 3.1886. Min Range: -3.1886

Max Act: 1.6087. Min Act: -0.0000

Data Index: 1279771 (C4 (Web Text))

Max Activating Token Index: 356

Text #6

Max Range: 3.1886. Min Range: -3.1886

Max Act: 1.5672. Min Act: -0.0000

Data Index: 613432 (C4 (Web Text))

Max Activating Token Index: 1016

Text #7

Max Range: 3.1886. Min Range: -3.1886

Max Act: 1.6818. Min Act: -0.0000

Data Index: 1121006 (C4 (Web Text))

Max Activating Token Index: 731

Text #8

Max Range: 3.1886. Min Range: -3.1886

Max Act: 1.3723. Min Act: -0.0000

Data Index: 1275740 (C4 (Web Text))

Max Activating Token Index: 828

Text #9

Max Range: 3.1886. Min Range: -3.1886

Max Act: 1.2327. Min Act: -0.0000

Data Index: 831254 (C4 (Web Text))

Max Activating Token Index: 833

Text #10

Max Range: 3.1886. Min Range: -3.1886

Max Act: 1.4319. Min Act: -0.0000

Data Index: 232100 (C4 (Web Text))

Max Activating Token Index: 757

Text #11

Max Range: 3.1886. Min Range: -3.1886

Max Act: 1.5862. Min Act: -0.0000

Data Index: 609937 (C4 (Web Text))

Max Activating Token Index: 711

Text #12

Max Range: 3.1886. Min Range: -3.1886

Max Act: 1.4364. Min Act: -0.0000

Data Index: 1175668 (C4 (Web Text))

Max Activating Token Index: 357

Text #13

Max Range: 3.1886. Min Range: -3.1886

Max Act: 1.4277. Min Act: -0.0000

Data Index: 1235131 (C4 (Web Text))

Max Activating Token Index: 254

Text #14

Max Range: 3.1886. Min Range: -3.1886

Max Act: 1.3761. Min Act: -0.0000

Data Index: 1195007 (C4 (Web Text))

Max Activating Token Index: 576

Text #15

Max Range: 3.1886. Min Range: -3.1886

Max Act: 1.2886. Min Act: -0.0000

Data Index: 1208672 (C4 (Web Text))

Max Activating Token Index: 749

Text #16

Max Range: 3.1886. Min Range: -3.1886

Max Act: 1.3761. Min Act: -0.0000

Data Index: 56427 (C4 (Web Text))

Max Activating Token Index: 902

Text #17

Max Range: 3.1886. Min Range: -3.1886

Max Act: 1.3579. Min Act: -0.0000

Data Index: 1303819 (C4 (Web Text))

Max Activating Token Index: 571

Text #18

Max Range: 3.1886. Min Range: -3.1886

Max Act: 1.3978. Min Act: -0.0000

Data Index: 263765 (C4 (Web Text))

Max Activating Token Index: 999

Text #19

Max Range: 3.1886. Min Range: -3.1886

Max Act: 1.3003. Min Act: -0.0000

Data Index: 479041 (C4 (Web Text))

Max Activating Token Index: 510