Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2808 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.8054. Min Range: -0.8054

Max Act: 0.8054. Min Act: -0.0000

Data Index: 8079 (C4 (Web Text))

Max Activating Token Index: 100

Text #1

Max Range: 0.8054. Min Range: -0.8054

Max Act: 0.7861. Min Act: -0.0000

Data Index: 167949 (C4 (Web Text))

Max Activating Token Index: 46

Text #2

Max Range: 0.8054. Min Range: -0.8054

Max Act: 0.7428. Min Act: -0.0000

Data Index: 326295 (C4 (Web Text))

Max Activating Token Index: 444

Text #3

Max Range: 0.8054. Min Range: -0.8054

Max Act: 0.7017. Min Act: -0.0000

Data Index: 939435 (C4 (Web Text))

Max Activating Token Index: 965

Text #4

Max Range: 0.8054. Min Range: -0.8054

Max Act: 0.7074. Min Act: -0.0000

Data Index: 1254367 (C4 (Web Text))

Max Activating Token Index: 59

Text #5

Max Range: 0.8054. Min Range: -0.8054

Max Act: 0.6708. Min Act: -0.0000

Data Index: 927213 (C4 (Web Text))

Max Activating Token Index: 357

Text #6

Max Range: 0.8054. Min Range: -0.8054

Max Act: 0.6401. Min Act: -0.0000

Data Index: 147514 (C4 (Web Text))

Max Activating Token Index: 35

Text #7

Max Range: 0.8054. Min Range: -0.8054

Max Act: 0.6950. Min Act: -0.0000

Data Index: 340243 (C4 (Web Text))

Max Activating Token Index: 9

Text #8

Max Range: 0.8054. Min Range: -0.8054

Max Act: 0.6291. Min Act: -0.0000

Data Index: 120125 (C4 (Web Text))

Max Activating Token Index: 223

Text #9

Max Range: 0.8054. Min Range: -0.8054

Max Act: 0.6412. Min Act: -0.0000

Data Index: 477425 (C4 (Web Text))

Max Activating Token Index: 652

Text #10

Max Range: 0.8054. Min Range: -0.8054

Max Act: 0.6516. Min Act: -0.0000

Data Index: 170758 (C4 (Web Text))

Max Activating Token Index: 971

Text #11

Max Range: 0.8054. Min Range: -0.8054

Max Act: 0.6391. Min Act: -0.0000

Data Index: 905044 (C4 (Web Text))

Max Activating Token Index: 294

Text #12

Max Range: 0.8054. Min Range: -0.8054

Max Act: 0.5645. Min Act: -0.0000

Data Index: 1136773 (C4 (Web Text))

Max Activating Token Index: 687

Text #13

Max Range: 0.8054. Min Range: -0.8054

Max Act: 0.5772. Min Act: -0.0000

Data Index: 289945 (C4 (Web Text))

Max Activating Token Index: 168

Text #14

Max Range: 0.8054. Min Range: -0.8054

Max Act: 0.6039. Min Act: -0.0000

Data Index: 206164 (C4 (Web Text))

Max Activating Token Index: 112

Text #15

Max Range: 0.8054. Min Range: -0.8054

Max Act: 0.5400. Min Act: -0.0000

Data Index: 416030 (C4 (Web Text))

Max Activating Token Index: 209

Text #16

Max Range: 0.8054. Min Range: -0.8054

Max Act: 0.5309. Min Act: -0.0000

Data Index: 1108190 (C4 (Web Text))

Max Activating Token Index: 549

Text #17

Max Range: 0.8054. Min Range: -0.8054

Max Act: 0.5361. Min Act: -0.0000

Data Index: 693856 (C4 (Web Text))

Max Activating Token Index: 993

Text #18

Max Range: 0.8054. Min Range: -0.8054

Max Act: 0.4942. Min Act: -0.0000

Data Index: 553483 (C4 (Web Text))

Max Activating Token Index: 94

Text #19

Max Range: 0.8054. Min Range: -0.8054

Max Act: 0.5126. Min Act: -0.0000

Data Index: 294944 (C4 (Web Text))

Max Activating Token Index: 870