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

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

Neuron 1558 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1078. Min Range: -0.1078

Max Act: 0.1078. Min Act: -0.0003

Data Index: 625684 (C4 (Web Text))

Max Activating Token Index: 52

Text #1

Max Range: 0.1078. Min Range: -0.1078

Max Act: 0.0956. Min Act: -0.0002

Data Index: 554923 (C4 (Web Text))

Max Activating Token Index: 192

Text #2

Max Range: 0.1078. Min Range: -0.1078

Max Act: 0.0915. Min Act: -0.0003

Data Index: 350786 (C4 (Web Text))

Max Activating Token Index: 193

Text #3

Max Range: 0.1078. Min Range: -0.1078

Max Act: 0.0898. Min Act: -0.0003

Data Index: 316824 (C4 (Web Text))

Max Activating Token Index: 336

Text #4

Max Range: 0.1078. Min Range: -0.1078

Max Act: 0.0906. Min Act: -0.0003

Data Index: 1209689 (C4 (Web Text))

Max Activating Token Index: 431

Text #5

Max Range: 0.1078. Min Range: -0.1078

Max Act: 0.0869. Min Act: -0.0003

Data Index: 263490 (C4 (Web Text))

Max Activating Token Index: 114

Text #6

Max Range: 0.1078. Min Range: -0.1078

Max Act: 0.0854. Min Act: -0.0003

Data Index: 763544 (C4 (Web Text))

Max Activating Token Index: 546

Text #7

Max Range: 0.1078. Min Range: -0.1078

Max Act: 0.0883. Min Act: -0.0003

Data Index: 807310 (C4 (Web Text))

Max Activating Token Index: 71

Text #8

Max Range: 0.1078. Min Range: -0.1078

Max Act: 0.0879. Min Act: -0.0003

Data Index: 82574 (C4 (Web Text))

Max Activating Token Index: 344

Text #9

Max Range: 0.1078. Min Range: -0.1078

Max Act: 0.0847. Min Act: -0.0003

Data Index: 1250555 (C4 (Web Text))

Max Activating Token Index: 100

Text #10

Max Range: 0.1078. Min Range: -0.1078

Max Act: 0.0845. Min Act: -0.0003

Data Index: 907786 (C4 (Web Text))

Max Activating Token Index: 439

Text #11

Max Range: 0.1078. Min Range: -0.1078

Max Act: 0.0811. Min Act: -0.0002

Data Index: 1229542 (C4 (Web Text))

Max Activating Token Index: 224

Text #12

Max Range: 0.1078. Min Range: -0.1078

Max Act: 0.0792. Min Act: -0.0003

Data Index: 1264044 (C4 (Web Text))

Max Activating Token Index: 726

Text #13

Max Range: 0.1078. Min Range: -0.1078

Max Act: 0.0832. Min Act: -0.0003

Data Index: 587816 (C4 (Web Text))

Max Activating Token Index: 26

Text #14

Max Range: 0.1078. Min Range: -0.1078

Max Act: 0.0834. Min Act: -0.0003

Data Index: 825063 (C4 (Web Text))

Max Activating Token Index: 616

Text #15

Max Range: 0.1078. Min Range: -0.1078

Max Act: 0.0806. Min Act: -0.0003

Data Index: 13314 (C4 (Web Text))

Max Activating Token Index: 495

Text #16

Max Range: 0.1078. Min Range: -0.1078

Max Act: 0.0781. Min Act: -0.0003

Data Index: 568898 (C4 (Web Text))

Max Activating Token Index: 133

Text #17

Max Range: 0.1078. Min Range: -0.1078

Max Act: 0.0787. Min Act: -0.0003

Data Index: 483345 (C4 (Web Text))

Max Activating Token Index: 85

Text #18

Max Range: 0.1078. Min Range: -0.1078

Max Act: 0.0826. Min Act: -0.0002

Data Index: 1155435 (C4 (Web Text))

Max Activating Token Index: 238

Text #19

Max Range: 0.1078. Min Range: -0.1078

Max Act: 0.0761. Min Act: -0.0002

Data Index: 640962 (C4 (Web Text))

Max Activating Token Index: 914