Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4083 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.8621. Min Range: -0.8621

Max Act: 0.8621. Min Act: -0.0000

Data Index: 1131481 (C4 (Web Text))

Max Activating Token Index: 185

Text #1

Max Range: 0.8621. Min Range: -0.8621

Max Act: 0.8365. Min Act: -0.0000

Data Index: 262922 (C4 (Web Text))

Max Activating Token Index: 119

Text #2

Max Range: 0.8621. Min Range: -0.8621

Max Act: 0.7332. Min Act: -0.0000

Data Index: 1084045 (C4 (Web Text))

Max Activating Token Index: 949

Text #3

Max Range: 0.8621. Min Range: -0.8621

Max Act: 0.7752. Min Act: -0.0000

Data Index: 970918 (C4 (Web Text))

Max Activating Token Index: 763

Text #4

Max Range: 0.8621. Min Range: -0.8621

Max Act: 0.7475. Min Act: -0.0000

Data Index: 719141 (C4 (Web Text))

Max Activating Token Index: 610

Text #5

Max Range: 0.8621. Min Range: -0.8621

Max Act: 0.7148. Min Act: -0.0000

Data Index: 489376 (C4 (Web Text))

Max Activating Token Index: 986

Text #6

Max Range: 0.8621. Min Range: -0.8621

Max Act: 0.7062. Min Act: -0.0000

Data Index: 849938 (C4 (Web Text))

Max Activating Token Index: 91

Text #7

Max Range: 0.8621. Min Range: -0.8621

Max Act: 0.7140. Min Act: -0.0000

Data Index: 274997 (C4 (Web Text))

Max Activating Token Index: 941

Text #8

Max Range: 0.8621. Min Range: -0.8621

Max Act: 0.6784. Min Act: -0.0000

Data Index: 562927 (C4 (Web Text))

Max Activating Token Index: 52

Text #9

Max Range: 0.8621. Min Range: -0.8621

Max Act: 0.7032. Min Act: -0.0000

Data Index: 989553 (C4 (Web Text))

Max Activating Token Index: 774

Text #10

Max Range: 0.8621. Min Range: -0.8621

Max Act: 0.6886. Min Act: -0.0000

Data Index: 906460 (C4 (Web Text))

Max Activating Token Index: 464

Text #11

Max Range: 0.8621. Min Range: -0.8621

Max Act: 0.7110. Min Act: -0.0000

Data Index: 1132289 (C4 (Web Text))

Max Activating Token Index: 691

Text #12

Max Range: 0.8621. Min Range: -0.8621

Max Act: 0.6831. Min Act: -0.0000

Data Index: 1183274 (C4 (Web Text))

Max Activating Token Index: 547

Text #13

Max Range: 0.8621. Min Range: -0.8621

Max Act: 0.6859. Min Act: -0.0000

Data Index: 1125060 (C4 (Web Text))

Max Activating Token Index: 844

Text #14

Max Range: 0.8621. Min Range: -0.8621

Max Act: 0.6755. Min Act: -0.0000

Data Index: 451319 (C4 (Web Text))

Max Activating Token Index: 879

Text #15

Max Range: 0.8621. Min Range: -0.8621

Max Act: 0.6910. Min Act: -0.0000

Data Index: 1093793 (C4 (Web Text))

Max Activating Token Index: 393

Text #16

Max Range: 0.8621. Min Range: -0.8621

Max Act: 0.6941. Min Act: -0.0000

Data Index: 43122 (C4 (Web Text))

Max Activating Token Index: 709

Text #17

Max Range: 0.8621. Min Range: -0.8621

Max Act: 0.6868. Min Act: -0.0000

Data Index: 640312 (C4 (Web Text))

Max Activating Token Index: 422

Text #18

Max Range: 0.8621. Min Range: -0.8621

Max Act: 0.6230. Min Act: -0.0000

Data Index: 406926 (C4 (Web Text))

Max Activating Token Index: 982

Text #19

Max Range: 0.8621. Min Range: -0.8621

Max Act: 0.6762. Min Act: -0.0000

Data Index: 1197078 (C4 (Web Text))

Max Activating Token Index: 713