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

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

Neuron 2170 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3894. Min Range: -2.3894

Max Act: 2.3894. Min Act: -0.0000

Data Index: 498022 (C4 (Web Text))

Max Activating Token Index: 506

Text #1

Max Range: 2.3894. Min Range: -2.3894

Max Act: 2.1156. Min Act: -0.0000

Data Index: 40762 (C4 (Web Text))

Max Activating Token Index: 1012

Text #2

Max Range: 2.3894. Min Range: -2.3894

Max Act: 2.1685. Min Act: -0.0000

Data Index: 258300 (C4 (Web Text))

Max Activating Token Index: 963

Text #3

Max Range: 2.3894. Min Range: -2.3894

Max Act: 2.1072. Min Act: -0.0000

Data Index: 155252 (C4 (Web Text))

Max Activating Token Index: 237

Text #4

Max Range: 2.3894. Min Range: -2.3894

Max Act: 1.6414. Min Act: -0.0000

Data Index: 456213 (C4 (Web Text))

Max Activating Token Index: 298

Text #5

Max Range: 2.3894. Min Range: -2.3894

Max Act: 1.4380. Min Act: -0.0000

Data Index: 616492 (C4 (Web Text))

Max Activating Token Index: 578

Text #6

Max Range: 2.3894. Min Range: -2.3894

Max Act: 1.3555. Min Act: -0.0000

Data Index: 864280 (C4 (Web Text))

Max Activating Token Index: 971

Text #7

Max Range: 2.3894. Min Range: -2.3894

Max Act: 1.4308. Min Act: -0.0000

Data Index: 1018522 (C4 (Web Text))

Max Activating Token Index: 806

Text #8

Max Range: 2.3894. Min Range: -2.3894

Max Act: 1.4245. Min Act: -0.0000

Data Index: 1615227 (Python Code)

Max Activating Token Index: 888

Text #9

Max Range: 2.3894. Min Range: -2.3894

Max Act: 1.2858. Min Act: -0.0000

Data Index: 182523 (C4 (Web Text))

Max Activating Token Index: 42

Text #10

Max Range: 2.3894. Min Range: -2.3894

Max Act: 1.2107. Min Act: -0.0000

Data Index: 97182 (C4 (Web Text))

Max Activating Token Index: 263

Text #11

Max Range: 2.3894. Min Range: -2.3894

Max Act: 1.2901. Min Act: -0.0000

Data Index: 1282660 (C4 (Web Text))

Max Activating Token Index: 384

Text #12

Max Range: 2.3894. Min Range: -2.3894

Max Act: 1.0079. Min Act: -0.0000

Data Index: 1103801 (C4 (Web Text))

Max Activating Token Index: 812

Text #13

Max Range: 2.3894. Min Range: -2.3894

Max Act: 1.2697. Min Act: -0.0000

Data Index: 706204 (C4 (Web Text))

Max Activating Token Index: 607

Text #14

Max Range: 2.3894. Min Range: -2.3894

Max Act: 1.2585. Min Act: -0.0000

Data Index: 1133683 (C4 (Web Text))

Max Activating Token Index: 400

Text #15

Max Range: 2.3894. Min Range: -2.3894

Max Act: 1.2497. Min Act: -0.0000

Data Index: 563737 (C4 (Web Text))

Max Activating Token Index: 649

Text #16

Max Range: 2.3894. Min Range: -2.3894

Max Act: 1.1721. Min Act: -0.0000

Data Index: 529754 (C4 (Web Text))

Max Activating Token Index: 248

Text #17

Max Range: 2.3894. Min Range: -2.3894

Max Act: 1.1613. Min Act: -0.0000

Data Index: 1105820 (C4 (Web Text))

Max Activating Token Index: 115

Text #18

Max Range: 2.3894. Min Range: -2.3894

Max Act: 1.1440. Min Act: -0.0000

Data Index: 37491 (C4 (Web Text))

Max Activating Token Index: 752

Text #19

Max Range: 2.3894. Min Range: -2.3894

Max Act: 1.0833. Min Act: -0.0000

Data Index: 1098575 (C4 (Web Text))

Max Activating Token Index: 282