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

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

Neuron 3027 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3691. Min Range: -1.3691

Max Act: 1.3691. Min Act: -0.0000

Data Index: 921976 (C4 (Web Text))

Max Activating Token Index: 847

Text #1

Max Range: 1.3691. Min Range: -1.3691

Max Act: 1.0964. Min Act: -0.0000

Data Index: 1115522 (C4 (Web Text))

Max Activating Token Index: 40

Text #2

Max Range: 1.3691. Min Range: -1.3691

Max Act: 1.0549. Min Act: -0.0000

Data Index: 1023036 (C4 (Web Text))

Max Activating Token Index: 440

Text #3

Max Range: 1.3691. Min Range: -1.3691

Max Act: 1.0684. Min Act: -0.0000

Data Index: 483361 (C4 (Web Text))

Max Activating Token Index: 125

Text #4

Max Range: 1.3691. Min Range: -1.3691

Max Act: 0.9953. Min Act: -0.0000

Data Index: 747736 (C4 (Web Text))

Max Activating Token Index: 527

Text #5

Max Range: 1.3691. Min Range: -1.3691

Max Act: 0.9803. Min Act: -0.0000

Data Index: 964687 (C4 (Web Text))

Max Activating Token Index: 986

Text #6

Max Range: 1.3691. Min Range: -1.3691

Max Act: 0.9611. Min Act: -0.0000

Data Index: 1100502 (C4 (Web Text))

Max Activating Token Index: 530

Text #7

Max Range: 1.3691. Min Range: -1.3691

Max Act: 0.9753. Min Act: -0.0000

Data Index: 839060 (C4 (Web Text))

Max Activating Token Index: 198

Text #8

Max Range: 1.3691. Min Range: -1.3691

Max Act: 1.0037. Min Act: -0.0000

Data Index: 1187630 (C4 (Web Text))

Max Activating Token Index: 303

Text #9

Max Range: 1.3691. Min Range: -1.3691

Max Act: 0.9400. Min Act: -0.0000

Data Index: 214670 (C4 (Web Text))

Max Activating Token Index: 985

Text #10

Max Range: 1.3691. Min Range: -1.3691

Max Act: 0.9352. Min Act: -0.0000

Data Index: 564631 (C4 (Web Text))

Max Activating Token Index: 139

Text #11

Max Range: 1.3691. Min Range: -1.3691

Max Act: 0.9311. Min Act: -0.0000

Data Index: 1171772 (C4 (Web Text))

Max Activating Token Index: 444

Text #12

Max Range: 1.3691. Min Range: -1.3691

Max Act: 0.9444. Min Act: -0.0000

Data Index: 290711 (C4 (Web Text))

Max Activating Token Index: 307

Text #13

Max Range: 1.3691. Min Range: -1.3691

Max Act: 0.8634. Min Act: -0.0000

Data Index: 639188 (C4 (Web Text))

Max Activating Token Index: 179

Text #14

Max Range: 1.3691. Min Range: -1.3691

Max Act: 0.9205. Min Act: -0.0000

Data Index: 1214638 (C4 (Web Text))

Max Activating Token Index: 759

Text #15

Max Range: 1.3691. Min Range: -1.3691

Max Act: 0.9196. Min Act: -0.0000

Data Index: 349546 (C4 (Web Text))

Max Activating Token Index: 344

Text #16

Max Range: 1.3691. Min Range: -1.3691

Max Act: 0.9097. Min Act: -0.0000

Data Index: 752009 (C4 (Web Text))

Max Activating Token Index: 92

Text #17

Max Range: 1.3691. Min Range: -1.3691

Max Act: 0.9378. Min Act: -0.0000

Data Index: 56172 (C4 (Web Text))

Max Activating Token Index: 127

Text #18

Max Range: 1.3691. Min Range: -1.3691

Max Act: 0.9151. Min Act: -0.0000

Data Index: 94705 (C4 (Web Text))

Max Activating Token Index: 994

Text #19

Max Range: 1.3691. Min Range: -1.3691

Max Act: 0.9220. Min Act: -0.0000

Data Index: 1046711 (C4 (Web Text))

Max Activating Token Index: 394