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

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

Neuron 165 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: 5.5996. Min Range: -5.5996

Max Act: 5.3916. Min Act: -0.0001

Data Index: 273187 (C4 (Web Text))

Max Activating Token Index: 726

Text #1

Max Range: 5.5996. Min Range: -5.5996

Max Act: 5.5996. Min Act: -0.0001

Data Index: 1080947 (C4 (Web Text))

Max Activating Token Index: 482

Text #2

Max Range: 5.5996. Min Range: -5.5996

Max Act: 4.9171. Min Act: -0.0001

Data Index: 872737 (C4 (Web Text))

Max Activating Token Index: 911

Text #3

Max Range: 5.5996. Min Range: -5.5996

Max Act: 4.8749. Min Act: -0.0001

Data Index: 1060945 (C4 (Web Text))

Max Activating Token Index: 359

Text #4

Max Range: 5.5996. Min Range: -5.5996

Max Act: 4.7118. Min Act: -0.0001

Data Index: 321755 (C4 (Web Text))

Max Activating Token Index: 571

Text #5

Max Range: 5.5996. Min Range: -5.5996

Max Act: 4.6046. Min Act: -0.0001

Data Index: 775732 (C4 (Web Text))

Max Activating Token Index: 50

Text #6

Max Range: 5.5996. Min Range: -5.5996

Max Act: 4.6593. Min Act: -0.0001

Data Index: 414359 (C4 (Web Text))

Max Activating Token Index: 262

Text #7

Max Range: 5.5996. Min Range: -5.5996

Max Act: 4.3689. Min Act: -0.0001

Data Index: 1063095 (C4 (Web Text))

Max Activating Token Index: 188

Text #8

Max Range: 5.5996. Min Range: -5.5996

Max Act: 4.5520. Min Act: -0.0001

Data Index: 1102443 (C4 (Web Text))

Max Activating Token Index: 187

Text #9

Max Range: 5.5996. Min Range: -5.5996

Max Act: 4.5211. Min Act: -0.0001

Data Index: 935206 (C4 (Web Text))

Max Activating Token Index: 114

Text #10

Max Range: 5.5996. Min Range: -5.5996

Max Act: 4.3200. Min Act: -0.0001

Data Index: 978299 (C4 (Web Text))

Max Activating Token Index: 116

Text #11

Max Range: 5.5996. Min Range: -5.5996

Max Act: 4.1248. Min Act: -0.0001

Data Index: 1092239 (C4 (Web Text))

Max Activating Token Index: 36

Text #12

Max Range: 5.5996. Min Range: -5.5996

Max Act: 4.1519. Min Act: -0.0001

Data Index: 550122 (C4 (Web Text))

Max Activating Token Index: 72

Text #13

Max Range: 5.5996. Min Range: -5.5996

Max Act: 3.7935. Min Act: -0.0001

Data Index: 740664 (C4 (Web Text))

Max Activating Token Index: 617

Text #14

Max Range: 5.5996. Min Range: -5.5996

Max Act: 4.2796. Min Act: -0.0001

Data Index: 917252 (C4 (Web Text))

Max Activating Token Index: 922

Text #15

Max Range: 5.5996. Min Range: -5.5996

Max Act: 3.9784. Min Act: -0.0001

Data Index: 1067248 (C4 (Web Text))

Max Activating Token Index: 512

Text #16

Max Range: 5.5996. Min Range: -5.5996

Max Act: 3.9430. Min Act: -0.0001

Data Index: 621488 (C4 (Web Text))

Max Activating Token Index: 571

Text #17

Max Range: 5.5996. Min Range: -5.5996

Max Act: 4.1948. Min Act: -0.0001

Data Index: 65846 (C4 (Web Text))

Max Activating Token Index: 676

Text #18

Max Range: 5.5996. Min Range: -5.5996

Max Act: 4.2039. Min Act: -0.0001

Data Index: 245265 (C4 (Web Text))

Max Activating Token Index: 210

Text #19

Max Range: 5.5996. Min Range: -5.5996

Max Act: 4.0205. Min Act: -0.0001

Data Index: 856764 (C4 (Web Text))

Max Activating Token Index: 26