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

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

Neuron 2775 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8121. Min Range: -0.8121

Max Act: 0.8121. Min Act: -0.0000

Data Index: 771214 (C4 (Web Text))

Max Activating Token Index: 988

Text #1

Max Range: 0.8121. Min Range: -0.8121

Max Act: 0.7958. Min Act: -0.0000

Data Index: 765905 (C4 (Web Text))

Max Activating Token Index: 896

Text #2

Max Range: 0.8121. Min Range: -0.8121

Max Act: 0.6474. Min Act: -0.0000

Data Index: 986051 (C4 (Web Text))

Max Activating Token Index: 903

Text #3

Max Range: 0.8121. Min Range: -0.8121

Max Act: 0.7279. Min Act: -0.0000

Data Index: 382484 (C4 (Web Text))

Max Activating Token Index: 974

Text #4

Max Range: 0.8121. Min Range: -0.8121

Max Act: 0.7564. Min Act: -0.0000

Data Index: 608614 (C4 (Web Text))

Max Activating Token Index: 1000

Text #5

Max Range: 0.8121. Min Range: -0.8121

Max Act: 0.7615. Min Act: -0.0000

Data Index: 451351 (C4 (Web Text))

Max Activating Token Index: 203

Text #6

Max Range: 0.8121. Min Range: -0.8121

Max Act: 0.7605. Min Act: -0.0000

Data Index: 673813 (C4 (Web Text))

Max Activating Token Index: 1015

Text #7

Max Range: 0.8121. Min Range: -0.8121

Max Act: 0.6602. Min Act: -0.0000

Data Index: 830349 (C4 (Web Text))

Max Activating Token Index: 282

Text #8

Max Range: 0.8121. Min Range: -0.8121

Max Act: 0.7056. Min Act: -0.0000

Data Index: 1193423 (C4 (Web Text))

Max Activating Token Index: 117

Text #9

Max Range: 0.8121. Min Range: -0.8121

Max Act: 0.7015. Min Act: -0.0000

Data Index: 654212 (C4 (Web Text))

Max Activating Token Index: 916

Text #10

Max Range: 0.8121. Min Range: -0.8121

Max Act: 0.7456. Min Act: -0.0000

Data Index: 307529 (C4 (Web Text))

Max Activating Token Index: 881

Text #11

Max Range: 0.8121. Min Range: -0.8121

Max Act: 0.7448. Min Act: -0.0000

Data Index: 80663 (C4 (Web Text))

Max Activating Token Index: 1021

Text #12

Max Range: 0.8121. Min Range: -0.8121

Max Act: 0.7210. Min Act: -0.0000

Data Index: 365526 (C4 (Web Text))

Max Activating Token Index: 258

Text #13

Max Range: 0.8121. Min Range: -0.8121

Max Act: 0.6914. Min Act: -0.0000

Data Index: 1228207 (C4 (Web Text))

Max Activating Token Index: 930

Text #14

Max Range: 0.8121. Min Range: -0.8121

Max Act: 0.7666. Min Act: -0.0000

Data Index: 918611 (C4 (Web Text))

Max Activating Token Index: 936

Text #15

Max Range: 0.8121. Min Range: -0.8121

Max Act: 0.7133. Min Act: -0.0000

Data Index: 739600 (C4 (Web Text))

Max Activating Token Index: 163

Text #16

Max Range: 0.8121. Min Range: -0.8121

Max Act: 0.6663. Min Act: -0.0000

Data Index: 946886 (C4 (Web Text))

Max Activating Token Index: 871

Text #17

Max Range: 0.8121. Min Range: -0.8121

Max Act: 0.7300. Min Act: -0.0000

Data Index: 311184 (C4 (Web Text))

Max Activating Token Index: 145

Text #18

Max Range: 0.8121. Min Range: -0.8121

Max Act: 0.7009. Min Act: -0.0000

Data Index: 1162193 (C4 (Web Text))

Max Activating Token Index: 79

Text #19

Max Range: 0.8121. Min Range: -0.8121

Max Act: 0.7024. Min Act: -0.0000

Data Index: 592377 (C4 (Web Text))

Max Activating Token Index: 950