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

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

Neuron 1089 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: 0.9996. Min Range: -0.9996

Max Act: 0.9699. Min Act: -0.0001

Data Index: 90360 (C4 (Web Text))

Max Activating Token Index: 3

Text #1

Max Range: 0.9996. Min Range: -0.9996

Max Act: 0.9562. Min Act: -0.0001

Data Index: 885515 (C4 (Web Text))

Max Activating Token Index: 94

Text #2

Max Range: 0.9996. Min Range: -0.9996

Max Act: 0.9996. Min Act: -0.0001

Data Index: 227078 (C4 (Web Text))

Max Activating Token Index: 836

Text #3

Max Range: 0.9996. Min Range: -0.9996

Max Act: 0.8577. Min Act: -0.0001

Data Index: 87133 (C4 (Web Text))

Max Activating Token Index: 916

Text #4

Max Range: 0.9996. Min Range: -0.9996

Max Act: 0.8493. Min Act: -0.0001

Data Index: 739165 (C4 (Web Text))

Max Activating Token Index: 934

Text #5

Max Range: 0.9996. Min Range: -0.9996

Max Act: 0.8710. Min Act: -0.0001

Data Index: 528437 (C4 (Web Text))

Max Activating Token Index: 154

Text #6

Max Range: 0.9996. Min Range: -0.9996

Max Act: 0.8380. Min Act: -0.0001

Data Index: 334204 (C4 (Web Text))

Max Activating Token Index: 32

Text #7

Max Range: 0.9996. Min Range: -0.9996

Max Act: 0.8083. Min Act: -0.0001

Data Index: 1323584 (C4 (Web Text))

Max Activating Token Index: 567

Text #8

Max Range: 0.9996. Min Range: -0.9996

Max Act: 0.8679. Min Act: -0.0001

Data Index: 14095 (C4 (Web Text))

Max Activating Token Index: 953

Text #9

Max Range: 0.9996. Min Range: -0.9996

Max Act: 0.8427. Min Act: -0.0001

Data Index: 1310341 (C4 (Web Text))

Max Activating Token Index: 793

Text #10

Max Range: 0.9996. Min Range: -0.9996

Max Act: 0.7301. Min Act: -0.0001

Data Index: 280179 (C4 (Web Text))

Max Activating Token Index: 93

Text #11

Max Range: 0.9996. Min Range: -0.9996

Max Act: 0.7368. Min Act: -0.0001

Data Index: 693566 (C4 (Web Text))

Max Activating Token Index: 81

Text #12

Max Range: 0.9996. Min Range: -0.9996

Max Act: 0.8327. Min Act: -0.0001

Data Index: 494087 (C4 (Web Text))

Max Activating Token Index: 26

Text #13

Max Range: 0.9996. Min Range: -0.9996

Max Act: 0.7322. Min Act: -0.0001

Data Index: 177793 (C4 (Web Text))

Max Activating Token Index: 746

Text #14

Max Range: 0.9996. Min Range: -0.9996

Max Act: 0.7422. Min Act: -0.0001

Data Index: 165210 (C4 (Web Text))

Max Activating Token Index: 410

Text #15

Max Range: 0.9996. Min Range: -0.9996

Max Act: 0.7862. Min Act: -0.0001

Data Index: 765180 (C4 (Web Text))

Max Activating Token Index: 743

Text #16

Max Range: 0.9996. Min Range: -0.9996

Max Act: 0.7509. Min Act: -0.0001

Data Index: 447375 (C4 (Web Text))

Max Activating Token Index: 815

Text #17

Max Range: 0.9996. Min Range: -0.9996

Max Act: 0.7244. Min Act: -0.0001

Data Index: 502459 (C4 (Web Text))

Max Activating Token Index: 724

Text #18

Max Range: 0.9996. Min Range: -0.9996

Max Act: 0.7742. Min Act: -0.0001

Data Index: 53285 (C4 (Web Text))

Max Activating Token Index: 199

Text #19

Max Range: 0.9996. Min Range: -0.9996

Max Act: 0.6670. Min Act: -0.0001

Data Index: 23816 (C4 (Web Text))

Max Activating Token Index: 824