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

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

Neuron 254 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.1040. Min Act: -0.0002

Data Index: 775950 (C4 (Web Text))

Max Activating Token Index: 550

Text #1

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0803. Min Act: -0.0002

Data Index: 93178 (C4 (Web Text))

Max Activating Token Index: 953

Text #2

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0779. Min Act: -0.0002

Data Index: 995992 (C4 (Web Text))

Max Activating Token Index: 51

Text #3

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0740. Min Act: -0.0002

Data Index: 944679 (C4 (Web Text))

Max Activating Token Index: 927

Text #4

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0732. Min Act: -0.0002

Data Index: 1148894 (C4 (Web Text))

Max Activating Token Index: 343

Text #5

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0713. Min Act: -0.0002

Data Index: 509853 (C4 (Web Text))

Max Activating Token Index: 729

Text #6

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0784. Min Act: -0.0002

Data Index: 668506 (C4 (Web Text))

Max Activating Token Index: 594

Text #7

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0643. Min Act: -0.0002

Data Index: 628130 (C4 (Web Text))

Max Activating Token Index: 299

Text #8

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0693. Min Act: -0.0002

Data Index: 1125118 (C4 (Web Text))

Max Activating Token Index: 644

Text #9

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0644. Min Act: -0.0002

Data Index: 859672 (C4 (Web Text))

Max Activating Token Index: 326

Text #10

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0710. Min Act: -0.0002

Data Index: 960148 (C4 (Web Text))

Max Activating Token Index: 198

Text #11

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0637. Min Act: -0.0002

Data Index: 878130 (C4 (Web Text))

Max Activating Token Index: 216

Text #12

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0731. Min Act: -0.0002

Data Index: 553445 (C4 (Web Text))

Max Activating Token Index: 709

Text #13

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0671. Min Act: -0.0002

Data Index: 615022 (C4 (Web Text))

Max Activating Token Index: 365

Text #14

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0605. Min Act: -0.0002

Data Index: 488745 (C4 (Web Text))

Max Activating Token Index: 286

Text #15

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0686. Min Act: -0.0002

Data Index: 1094430 (C4 (Web Text))

Max Activating Token Index: 535

Text #16

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0637. Min Act: -0.0002

Data Index: 1017792 (C4 (Web Text))

Max Activating Token Index: 32

Text #17

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0702. Min Act: -0.0002

Data Index: 970068 (C4 (Web Text))

Max Activating Token Index: 679

Text #18

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0677. Min Act: -0.0002

Data Index: 1288720 (C4 (Web Text))

Max Activating Token Index: 489

Text #19

Max Range: 0.1040. Min Range: -0.1040

Max Act: 0.0624. Min Act: -0.0002

Data Index: 534034 (C4 (Web Text))

Max Activating Token Index: 371