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

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

Neuron 2973 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0972. Min Range: -1.0972

Max Act: 1.0972. Min Act: -0.0000

Data Index: 945523 (C4 (Web Text))

Max Activating Token Index: 854

Text #1

Max Range: 1.0972. Min Range: -1.0972

Max Act: 0.9693. Min Act: -0.0000

Data Index: 703636 (C4 (Web Text))

Max Activating Token Index: 623

Text #2

Max Range: 1.0972. Min Range: -1.0972

Max Act: 0.9249. Min Act: -0.0000

Data Index: 30608 (C4 (Web Text))

Max Activating Token Index: 464

Text #3

Max Range: 1.0972. Min Range: -1.0972

Max Act: 0.8586. Min Act: -0.0000

Data Index: 146859 (C4 (Web Text))

Max Activating Token Index: 611

Text #4

Max Range: 1.0972. Min Range: -1.0972

Max Act: 0.9107. Min Act: -0.0000

Data Index: 1098359 (C4 (Web Text))

Max Activating Token Index: 881

Text #5

Max Range: 1.0972. Min Range: -1.0972

Max Act: 0.8826. Min Act: -0.0000

Data Index: 210859 (C4 (Web Text))

Max Activating Token Index: 192

Text #6

Max Range: 1.0972. Min Range: -1.0972

Max Act: 0.8612. Min Act: -0.0000

Data Index: 681940 (C4 (Web Text))

Max Activating Token Index: 615

Text #7

Max Range: 1.0972. Min Range: -1.0972

Max Act: 0.8775. Min Act: -0.0000

Data Index: 805536 (C4 (Web Text))

Max Activating Token Index: 240

Text #8

Max Range: 1.0972. Min Range: -1.0972

Max Act: 0.8065. Min Act: -0.0000

Data Index: 1229296 (C4 (Web Text))

Max Activating Token Index: 892

Text #9

Max Range: 1.0972. Min Range: -1.0972

Max Act: 0.8088. Min Act: -0.0000

Data Index: 924906 (C4 (Web Text))

Max Activating Token Index: 677

Text #10

Max Range: 1.0972. Min Range: -1.0972

Max Act: 0.8679. Min Act: -0.0000

Data Index: 628715 (C4 (Web Text))

Max Activating Token Index: 84

Text #11

Max Range: 1.0972. Min Range: -1.0972

Max Act: 0.8231. Min Act: -0.0000

Data Index: 17232 (C4 (Web Text))

Max Activating Token Index: 811

Text #12

Max Range: 1.0972. Min Range: -1.0972

Max Act: 0.8257. Min Act: -0.0000

Data Index: 420046 (C4 (Web Text))

Max Activating Token Index: 687

Text #13

Max Range: 1.0972. Min Range: -1.0972

Max Act: 0.7916. Min Act: -0.0000

Data Index: 1134918 (C4 (Web Text))

Max Activating Token Index: 505

Text #14

Max Range: 1.0972. Min Range: -1.0972

Max Act: 0.8059. Min Act: -0.0000

Data Index: 617307 (C4 (Web Text))

Max Activating Token Index: 384

Text #15

Max Range: 1.0972. Min Range: -1.0972

Max Act: 0.8096. Min Act: -0.0000

Data Index: 74162 (C4 (Web Text))

Max Activating Token Index: 1003

Text #16

Max Range: 1.0972. Min Range: -1.0972

Max Act: 0.7654. Min Act: -0.0000

Data Index: 684309 (C4 (Web Text))

Max Activating Token Index: 978

Text #17

Max Range: 1.0972. Min Range: -1.0972

Max Act: 0.8164. Min Act: -0.0000

Data Index: 565706 (C4 (Web Text))

Max Activating Token Index: 237

Text #18

Max Range: 1.0972. Min Range: -1.0972

Max Act: 0.7741. Min Act: -0.0000

Data Index: 580202 (C4 (Web Text))

Max Activating Token Index: 124

Text #19

Max Range: 1.0972. Min Range: -1.0972

Max Act: 0.8125. Min Act: -0.0000

Data Index: 1315483 (C4 (Web Text))

Max Activating Token Index: 398