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

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

Neuron 302 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5363. Min Range: -2.5363

Max Act: 2.3065. Min Act: -0.0000

Data Index: 636829 (C4 (Web Text))

Max Activating Token Index: 953

Text #1

Max Range: 2.5363. Min Range: -2.5363

Max Act: 2.4410. Min Act: -0.0000

Data Index: 355513 (C4 (Web Text))

Max Activating Token Index: 434

Text #2

Max Range: 2.5363. Min Range: -2.5363

Max Act: 2.5363. Min Act: -0.0000

Data Index: 1321850 (C4 (Web Text))

Max Activating Token Index: 917

Text #3

Max Range: 2.5363. Min Range: -2.5363

Max Act: 1.9493. Min Act: -0.0000

Data Index: 867848 (C4 (Web Text))

Max Activating Token Index: 100

Text #4

Max Range: 2.5363. Min Range: -2.5363

Max Act: 2.2017. Min Act: -0.0000

Data Index: 572629 (C4 (Web Text))

Max Activating Token Index: 508

Text #5

Max Range: 2.5363. Min Range: -2.5363

Max Act: 2.0651. Min Act: -0.0000

Data Index: 115087 (C4 (Web Text))

Max Activating Token Index: 88

Text #6

Max Range: 2.5363. Min Range: -2.5363

Max Act: 2.3032. Min Act: -0.0000

Data Index: 11970 (C4 (Web Text))

Max Activating Token Index: 989

Text #7

Max Range: 2.5363. Min Range: -2.5363

Max Act: 2.0603. Min Act: -0.0000

Data Index: 363820 (C4 (Web Text))

Max Activating Token Index: 78

Text #8

Max Range: 2.5363. Min Range: -2.5363

Max Act: 2.1313. Min Act: -0.0000

Data Index: 1052106 (C4 (Web Text))

Max Activating Token Index: 496

Text #9

Max Range: 2.5363. Min Range: -2.5363

Max Act: 2.3739. Min Act: -0.0000

Data Index: 1225793 (C4 (Web Text))

Max Activating Token Index: 695

Text #10

Max Range: 2.5363. Min Range: -2.5363

Max Act: 2.1097. Min Act: -0.0000

Data Index: 1078274 (C4 (Web Text))

Max Activating Token Index: 656

Text #11

Max Range: 2.5363. Min Range: -2.5363

Max Act: 2.2082. Min Act: -0.0000

Data Index: 100226 (C4 (Web Text))

Max Activating Token Index: 357

Text #12

Max Range: 2.5363. Min Range: -2.5363

Max Act: 2.0803. Min Act: -0.0000

Data Index: 157654 (C4 (Web Text))

Max Activating Token Index: 513

Text #13

Max Range: 2.5363. Min Range: -2.5363

Max Act: 2.1889. Min Act: -0.0000

Data Index: 95127 (C4 (Web Text))

Max Activating Token Index: 497

Text #14

Max Range: 2.5363. Min Range: -2.5363

Max Act: 2.1579. Min Act: -0.0000

Data Index: 1193502 (C4 (Web Text))

Max Activating Token Index: 838

Text #15

Max Range: 2.5363. Min Range: -2.5363

Max Act: 2.0584. Min Act: -0.0000

Data Index: 303750 (C4 (Web Text))

Max Activating Token Index: 45

Text #16

Max Range: 2.5363. Min Range: -2.5363

Max Act: 2.3690. Min Act: -0.0000

Data Index: 1025418 (C4 (Web Text))

Max Activating Token Index: 626

Text #17

Max Range: 2.5363. Min Range: -2.5363

Max Act: 1.9947. Min Act: -0.0000

Data Index: 725113 (C4 (Web Text))

Max Activating Token Index: 236

Text #18

Max Range: 2.5363. Min Range: -2.5363

Max Act: 1.9910. Min Act: -0.0000

Data Index: 888358 (C4 (Web Text))

Max Activating Token Index: 511

Text #19

Max Range: 2.5363. Min Range: -2.5363

Max Act: 2.2867. Min Act: -0.0000

Data Index: 1262223 (C4 (Web Text))

Max Activating Token Index: 198