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

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

Neuron 4196 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5715. Min Range: -0.5715

Max Act: 0.5715. Min Act: -0.0001

Data Index: 728341 (C4 (Web Text))

Max Activating Token Index: 81

Text #1

Max Range: 0.5715. Min Range: -0.5715

Max Act: 0.5365. Min Act: -0.0001

Data Index: 733746 (C4 (Web Text))

Max Activating Token Index: 460

Text #2

Max Range: 0.5715. Min Range: -0.5715

Max Act: 0.4464. Min Act: -0.0001

Data Index: 950786 (C4 (Web Text))

Max Activating Token Index: 68

Text #3

Max Range: 0.5715. Min Range: -0.5715

Max Act: 0.4565. Min Act: -0.0001

Data Index: 1138918 (C4 (Web Text))

Max Activating Token Index: 261

Text #4

Max Range: 0.5715. Min Range: -0.5715

Max Act: 0.4297. Min Act: -0.0001

Data Index: 1241546 (C4 (Web Text))

Max Activating Token Index: 620

Text #5

Max Range: 0.5715. Min Range: -0.5715

Max Act: 0.4519. Min Act: -0.0001

Data Index: 1118084 (C4 (Web Text))

Max Activating Token Index: 498

Text #6

Max Range: 0.5715. Min Range: -0.5715

Max Act: 0.4574. Min Act: -0.0001

Data Index: 816666 (C4 (Web Text))

Max Activating Token Index: 104

Text #7

Max Range: 0.5715. Min Range: -0.5715

Max Act: 0.4070. Min Act: -0.0001

Data Index: 1016509 (C4 (Web Text))

Max Activating Token Index: 169

Text #8

Max Range: 0.5715. Min Range: -0.5715

Max Act: 0.4332. Min Act: -0.0001

Data Index: 1042478 (C4 (Web Text))

Max Activating Token Index: 261

Text #9

Max Range: 0.5715. Min Range: -0.5715

Max Act: 0.4465. Min Act: -0.0001

Data Index: 1333143 (C4 (Web Text))

Max Activating Token Index: 31

Text #10

Max Range: 0.5715. Min Range: -0.5715

Max Act: 0.4472. Min Act: -0.0001

Data Index: 454905 (C4 (Web Text))

Max Activating Token Index: 157

Text #11

Max Range: 0.5715. Min Range: -0.5715

Max Act: 0.3929. Min Act: -0.0001

Data Index: 881564 (C4 (Web Text))

Max Activating Token Index: 870

Text #12

Max Range: 0.5715. Min Range: -0.5715

Max Act: 0.4223. Min Act: -0.0001

Data Index: 954305 (C4 (Web Text))

Max Activating Token Index: 947

Text #13

Max Range: 0.5715. Min Range: -0.5715

Max Act: 0.4288. Min Act: -0.0001

Data Index: 1256105 (C4 (Web Text))

Max Activating Token Index: 792

Text #14

Max Range: 0.5715. Min Range: -0.5715

Max Act: 0.3957. Min Act: -0.0001

Data Index: 613056 (C4 (Web Text))

Max Activating Token Index: 13

Text #15

Max Range: 0.5715. Min Range: -0.5715

Max Act: 0.4112. Min Act: -0.0001

Data Index: 346569 (C4 (Web Text))

Max Activating Token Index: 7

Text #16

Max Range: 0.5715. Min Range: -0.5715

Max Act: 0.3831. Min Act: -0.0001

Data Index: 1247563 (C4 (Web Text))

Max Activating Token Index: 368

Text #17

Max Range: 0.5715. Min Range: -0.5715

Max Act: 0.4187. Min Act: -0.0001

Data Index: 952662 (C4 (Web Text))

Max Activating Token Index: 149

Text #18

Max Range: 0.5715. Min Range: -0.5715

Max Act: 0.4187. Min Act: -0.0001

Data Index: 466869 (C4 (Web Text))

Max Activating Token Index: 973

Text #19

Max Range: 0.5715. Min Range: -0.5715

Max Act: 0.3894. Min Act: -0.0001

Data Index: 1225794 (C4 (Web Text))

Max Activating Token Index: 67