Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2870 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.8826. Min Range: -1.8826

Max Act: 1.8826. Min Act: -0.0001

Data Index: 998104 (C4 (Web Text))

Max Activating Token Index: 953

Text #1

Max Range: 1.8826. Min Range: -1.8826

Max Act: 1.8092. Min Act: -0.0000

Data Index: 723581 (C4 (Web Text))

Max Activating Token Index: 868

Text #2

Max Range: 1.8826. Min Range: -1.8826

Max Act: 1.6706. Min Act: -0.0000

Data Index: 451883 (C4 (Web Text))

Max Activating Token Index: 429

Text #3

Max Range: 1.8826. Min Range: -1.8826

Max Act: 1.6022. Min Act: -0.0001

Data Index: 683756 (C4 (Web Text))

Max Activating Token Index: 779

Text #4

Max Range: 1.8826. Min Range: -1.8826

Max Act: 1.5796. Min Act: -0.0000

Data Index: 67035 (C4 (Web Text))

Max Activating Token Index: 43

Text #5

Max Range: 1.8826. Min Range: -1.8826

Max Act: 1.4574. Min Act: -0.0000

Data Index: 127753 (C4 (Web Text))

Max Activating Token Index: 686

Text #6

Max Range: 1.8826. Min Range: -1.8826

Max Act: 1.3427. Min Act: -0.0000

Data Index: 143293 (C4 (Web Text))

Max Activating Token Index: 1003

Text #7

Max Range: 1.8826. Min Range: -1.8826

Max Act: 1.3356. Min Act: -0.0001

Data Index: 1290508 (C4 (Web Text))

Max Activating Token Index: 161

Text #8

Max Range: 1.8826. Min Range: -1.8826

Max Act: 1.2925. Min Act: -0.0000

Data Index: 1213587 (C4 (Web Text))

Max Activating Token Index: 147

Text #9

Max Range: 1.8826. Min Range: -1.8826

Max Act: 1.2919. Min Act: -0.0001

Data Index: 669334 (C4 (Web Text))

Max Activating Token Index: 514

Text #10

Max Range: 1.8826. Min Range: -1.8826

Max Act: 1.2107. Min Act: -0.0001

Data Index: 1217129 (C4 (Web Text))

Max Activating Token Index: 678

Text #11

Max Range: 1.8826. Min Range: -1.8826

Max Act: 1.2769. Min Act: -0.0001

Data Index: 66670 (C4 (Web Text))

Max Activating Token Index: 923

Text #12

Max Range: 1.8826. Min Range: -1.8826

Max Act: 1.3085. Min Act: -0.0000

Data Index: 812581 (C4 (Web Text))

Max Activating Token Index: 372

Text #13

Max Range: 1.8826. Min Range: -1.8826

Max Act: 1.2976. Min Act: -0.0000

Data Index: 724519 (C4 (Web Text))

Max Activating Token Index: 969

Text #14

Max Range: 1.8826. Min Range: -1.8826

Max Act: 1.2524. Min Act: -0.0000

Data Index: 73746 (C4 (Web Text))

Max Activating Token Index: 1016

Text #15

Max Range: 1.8826. Min Range: -1.8826

Max Act: 1.1849. Min Act: -0.0001

Data Index: 273505 (C4 (Web Text))

Max Activating Token Index: 887

Text #16

Max Range: 1.8826. Min Range: -1.8826

Max Act: 1.2433. Min Act: -0.0000

Data Index: 807978 (C4 (Web Text))

Max Activating Token Index: 337

Text #17

Max Range: 1.8826. Min Range: -1.8826

Max Act: 1.2396. Min Act: -0.0001

Data Index: 1277062 (C4 (Web Text))

Max Activating Token Index: 368

Text #18

Max Range: 1.8826. Min Range: -1.8826

Max Act: 1.1781. Min Act: -0.0000

Data Index: 4156 (C4 (Web Text))

Max Activating Token Index: 578

Text #19

Max Range: 1.8826. Min Range: -1.8826

Max Act: 1.1504. Min Act: -0.0000

Data Index: 482278 (C4 (Web Text))

Max Activating Token Index: 90