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

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

Neuron 3120 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3115. Min Range: -1.3115

Max Act: 1.3115. Min Act: -0.0001

Data Index: 1169565 (C4 (Web Text))

Max Activating Token Index: 273

Text #1

Max Range: 1.3115. Min Range: -1.3115

Max Act: 1.2285. Min Act: -0.0001

Data Index: 1243822 (C4 (Web Text))

Max Activating Token Index: 851

Text #2

Max Range: 1.3115. Min Range: -1.3115

Max Act: 1.2559. Min Act: -0.0001

Data Index: 212521 (C4 (Web Text))

Max Activating Token Index: 540

Text #3

Max Range: 1.3115. Min Range: -1.3115

Max Act: 1.2484. Min Act: -0.0001

Data Index: 1255655 (C4 (Web Text))

Max Activating Token Index: 782

Text #4

Max Range: 1.3115. Min Range: -1.3115

Max Act: 1.2018. Min Act: -0.0001

Data Index: 100420 (C4 (Web Text))

Max Activating Token Index: 840

Text #5

Max Range: 1.3115. Min Range: -1.3115

Max Act: 1.2085. Min Act: -0.0001

Data Index: 847113 (C4 (Web Text))

Max Activating Token Index: 787

Text #6

Max Range: 1.3115. Min Range: -1.3115

Max Act: 1.1992. Min Act: -0.0001

Data Index: 331603 (C4 (Web Text))

Max Activating Token Index: 977

Text #7

Max Range: 1.3115. Min Range: -1.3115

Max Act: 1.1626. Min Act: -0.0001

Data Index: 99089 (C4 (Web Text))

Max Activating Token Index: 754

Text #8

Max Range: 1.3115. Min Range: -1.3115

Max Act: 1.1235. Min Act: -0.0001

Data Index: 192993 (C4 (Web Text))

Max Activating Token Index: 627

Text #9

Max Range: 1.3115. Min Range: -1.3115

Max Act: 1.1585. Min Act: -0.0001

Data Index: 634143 (C4 (Web Text))

Max Activating Token Index: 971

Text #10

Max Range: 1.3115. Min Range: -1.3115

Max Act: 1.1280. Min Act: -0.0001

Data Index: 722416 (C4 (Web Text))

Max Activating Token Index: 652

Text #11

Max Range: 1.3115. Min Range: -1.3115

Max Act: 1.1630. Min Act: -0.0001

Data Index: 1263527 (C4 (Web Text))

Max Activating Token Index: 81

Text #12

Max Range: 1.3115. Min Range: -1.3115

Max Act: 1.1637. Min Act: -0.0001

Data Index: 719271 (C4 (Web Text))

Max Activating Token Index: 844

Text #13

Max Range: 1.3115. Min Range: -1.3115

Max Act: 1.1169. Min Act: -0.0001

Data Index: 692136 (C4 (Web Text))

Max Activating Token Index: 838

Text #14

Max Range: 1.3115. Min Range: -1.3115

Max Act: 1.1434. Min Act: -0.0001

Data Index: 984652 (C4 (Web Text))

Max Activating Token Index: 794

Text #15

Max Range: 1.3115. Min Range: -1.3115

Max Act: 1.1269. Min Act: -0.0001

Data Index: 665424 (C4 (Web Text))

Max Activating Token Index: 811

Text #16

Max Range: 1.3115. Min Range: -1.3115

Max Act: 1.1249. Min Act: -0.0001

Data Index: 1202954 (C4 (Web Text))

Max Activating Token Index: 908

Text #17

Max Range: 1.3115. Min Range: -1.3115

Max Act: 1.0808. Min Act: -0.0001

Data Index: 1185453 (C4 (Web Text))

Max Activating Token Index: 953

Text #18

Max Range: 1.3115. Min Range: -1.3115

Max Act: 1.1187. Min Act: -0.0001

Data Index: 981155 (C4 (Web Text))

Max Activating Token Index: 806

Text #19

Max Range: 1.3115. Min Range: -1.3115

Max Act: 1.0819. Min Act: -0.0001

Data Index: 638535 (C4 (Web Text))

Max Activating Token Index: 939