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

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

Neuron 607 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: 1.0631. Min Range: -1.0631

Max Act: 1.0631. Min Act: -0.0001

Data Index: 1130913 (C4 (Web Text))

Max Activating Token Index: 164

Text #1

Max Range: 1.0631. Min Range: -1.0631

Max Act: 0.9616. Min Act: -0.0001

Data Index: 594581 (C4 (Web Text))

Max Activating Token Index: 224

Text #2

Max Range: 1.0631. Min Range: -1.0631

Max Act: 0.9762. Min Act: -0.0001

Data Index: 367707 (C4 (Web Text))

Max Activating Token Index: 620

Text #3

Max Range: 1.0631. Min Range: -1.0631

Max Act: 0.9493. Min Act: -0.0001

Data Index: 86954 (C4 (Web Text))

Max Activating Token Index: 197

Text #4

Max Range: 1.0631. Min Range: -1.0631

Max Act: 0.9414. Min Act: -0.0001

Data Index: 412440 (C4 (Web Text))

Max Activating Token Index: 938

Text #5

Max Range: 1.0631. Min Range: -1.0631

Max Act: 1.0051. Min Act: -0.0001

Data Index: 495706 (C4 (Web Text))

Max Activating Token Index: 828

Text #6

Max Range: 1.0631. Min Range: -1.0631

Max Act: 0.9029. Min Act: -0.0001

Data Index: 1166042 (C4 (Web Text))

Max Activating Token Index: 688

Text #7

Max Range: 1.0631. Min Range: -1.0631

Max Act: 0.9056. Min Act: -0.0001

Data Index: 1235033 (C4 (Web Text))

Max Activating Token Index: 482

Text #8

Max Range: 1.0631. Min Range: -1.0631

Max Act: 0.8728. Min Act: -0.0001

Data Index: 1299710 (C4 (Web Text))

Max Activating Token Index: 825

Text #9

Max Range: 1.0631. Min Range: -1.0631

Max Act: 0.8823. Min Act: -0.0001

Data Index: 170094 (C4 (Web Text))

Max Activating Token Index: 511

Text #10

Max Range: 1.0631. Min Range: -1.0631

Max Act: 0.8905. Min Act: -0.0001

Data Index: 196394 (C4 (Web Text))

Max Activating Token Index: 1005

Text #11

Max Range: 1.0631. Min Range: -1.0631

Max Act: 0.8839. Min Act: -0.0001

Data Index: 1123596 (C4 (Web Text))

Max Activating Token Index: 163

Text #12

Max Range: 1.0631. Min Range: -1.0631

Max Act: 0.9114. Min Act: -0.0001

Data Index: 560061 (C4 (Web Text))

Max Activating Token Index: 183

Text #13

Max Range: 1.0631. Min Range: -1.0631

Max Act: 0.8841. Min Act: -0.0001

Data Index: 715334 (C4 (Web Text))

Max Activating Token Index: 254

Text #14

Max Range: 1.0631. Min Range: -1.0631

Max Act: 0.8733. Min Act: -0.0001

Data Index: 1052288 (C4 (Web Text))

Max Activating Token Index: 1012

Text #15

Max Range: 1.0631. Min Range: -1.0631

Max Act: 0.7850. Min Act: -0.0001

Data Index: 1051704 (C4 (Web Text))

Max Activating Token Index: 841

Text #16

Max Range: 1.0631. Min Range: -1.0631

Max Act: 0.8060. Min Act: -0.0001

Data Index: 432477 (C4 (Web Text))

Max Activating Token Index: 756

Text #17

Max Range: 1.0631. Min Range: -1.0631

Max Act: 0.8406. Min Act: -0.0001

Data Index: 262668 (C4 (Web Text))

Max Activating Token Index: 564

Text #18

Max Range: 1.0631. Min Range: -1.0631

Max Act: 0.8358. Min Act: -0.0001

Data Index: 1113674 (C4 (Web Text))

Max Activating Token Index: 960

Text #19

Max Range: 1.0631. Min Range: -1.0631

Max Act: 0.8036. Min Act: -0.0001

Data Index: 553405 (C4 (Web Text))

Max Activating Token Index: 45