Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1001 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.2051. Min Range: -1.2051

Max Act: 1.1501. Min Act: -0.0001

Data Index: 653786 (C4 (Web Text))

Max Activating Token Index: 906

Text #1

Max Range: 1.2051. Min Range: -1.2051

Max Act: 1.2051. Min Act: -0.0001

Data Index: 639283 (C4 (Web Text))

Max Activating Token Index: 791

Text #2

Max Range: 1.2051. Min Range: -1.2051

Max Act: 1.1861. Min Act: -0.0001

Data Index: 1020573 (C4 (Web Text))

Max Activating Token Index: 346

Text #3

Max Range: 1.2051. Min Range: -1.2051

Max Act: 1.1051. Min Act: -0.0001

Data Index: 300476 (C4 (Web Text))

Max Activating Token Index: 12

Text #4

Max Range: 1.2051. Min Range: -1.2051

Max Act: 1.1091. Min Act: -0.0001

Data Index: 196838 (C4 (Web Text))

Max Activating Token Index: 659

Text #5

Max Range: 1.2051. Min Range: -1.2051

Max Act: 1.0782. Min Act: -0.0001

Data Index: 912698 (C4 (Web Text))

Max Activating Token Index: 1008

Text #6

Max Range: 1.2051. Min Range: -1.2051

Max Act: 1.0481. Min Act: -0.0001

Data Index: 269635 (C4 (Web Text))

Max Activating Token Index: 53

Text #7

Max Range: 1.2051. Min Range: -1.2051

Max Act: 1.0183. Min Act: -0.0001

Data Index: 1070013 (C4 (Web Text))

Max Activating Token Index: 952

Text #8

Max Range: 1.2051. Min Range: -1.2051

Max Act: 1.0954. Min Act: -0.0001

Data Index: 1175725 (C4 (Web Text))

Max Activating Token Index: 812

Text #9

Max Range: 1.2051. Min Range: -1.2051

Max Act: 1.0469. Min Act: -0.0001

Data Index: 1269857 (C4 (Web Text))

Max Activating Token Index: 990

Text #10

Max Range: 1.2051. Min Range: -1.2051

Max Act: 1.0425. Min Act: -0.0001

Data Index: 1102034 (C4 (Web Text))

Max Activating Token Index: 778

Text #11

Max Range: 1.2051. Min Range: -1.2051

Max Act: 1.0050. Min Act: -0.0001

Data Index: 769952 (C4 (Web Text))

Max Activating Token Index: 472

Text #12

Max Range: 1.2051. Min Range: -1.2051

Max Act: 1.0246. Min Act: -0.0001

Data Index: 1220286 (C4 (Web Text))

Max Activating Token Index: 116

Text #13

Max Range: 1.2051. Min Range: -1.2051

Max Act: 1.0516. Min Act: -0.0001

Data Index: 336455 (C4 (Web Text))

Max Activating Token Index: 5

Text #14

Max Range: 1.2051. Min Range: -1.2051

Max Act: 1.0303. Min Act: -0.0001

Data Index: 168976 (C4 (Web Text))

Max Activating Token Index: 988

Text #15

Max Range: 1.2051. Min Range: -1.2051

Max Act: 1.0503. Min Act: -0.0001

Data Index: 1269118 (C4 (Web Text))

Max Activating Token Index: 9

Text #16

Max Range: 1.2051. Min Range: -1.2051

Max Act: 1.0411. Min Act: -0.0001

Data Index: 180539 (C4 (Web Text))

Max Activating Token Index: 887

Text #17

Max Range: 1.2051. Min Range: -1.2051

Max Act: 1.1124. Min Act: -0.0001

Data Index: 482966 (C4 (Web Text))

Max Activating Token Index: 715

Text #18

Max Range: 1.2051. Min Range: -1.2051

Max Act: 1.0122. Min Act: -0.0001

Data Index: 1320767 (C4 (Web Text))

Max Activating Token Index: 162

Text #19

Max Range: 1.2051. Min Range: -1.2051

Max Act: 1.0197. Min Act: -0.0001

Data Index: 256660 (C4 (Web Text))

Max Activating Token Index: 551