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

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

Neuron 5718 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3876. Min Range: -1.3876

Max Act: 1.3392. Min Act: -0.0001

Data Index: 623926 (C4 (Web Text))

Max Activating Token Index: 504

Text #1

Max Range: 1.3876. Min Range: -1.3876

Max Act: 1.3876. Min Act: -0.0001

Data Index: 411081 (C4 (Web Text))

Max Activating Token Index: 9

Text #2

Max Range: 1.3876. Min Range: -1.3876

Max Act: 1.2220. Min Act: -0.0001

Data Index: 321580 (C4 (Web Text))

Max Activating Token Index: 745

Text #3

Max Range: 1.3876. Min Range: -1.3876

Max Act: 1.1934. Min Act: -0.0001

Data Index: 451640 (C4 (Web Text))

Max Activating Token Index: 920

Text #4

Max Range: 1.3876. Min Range: -1.3876

Max Act: 1.0974. Min Act: -0.0001

Data Index: 1125047 (C4 (Web Text))

Max Activating Token Index: 256

Text #5

Max Range: 1.3876. Min Range: -1.3876

Max Act: 1.1579. Min Act: -0.0001

Data Index: 203841 (C4 (Web Text))

Max Activating Token Index: 20

Text #6

Max Range: 1.3876. Min Range: -1.3876

Max Act: 1.1157. Min Act: -0.0001

Data Index: 1155527 (C4 (Web Text))

Max Activating Token Index: 30

Text #7

Max Range: 1.3876. Min Range: -1.3876

Max Act: 1.1017. Min Act: -0.0001

Data Index: 457794 (C4 (Web Text))

Max Activating Token Index: 32

Text #8

Max Range: 1.3876. Min Range: -1.3876

Max Act: 1.0771. Min Act: -0.0001

Data Index: 1217182 (C4 (Web Text))

Max Activating Token Index: 988

Text #9

Max Range: 1.3876. Min Range: -1.3876

Max Act: 1.0986. Min Act: -0.0000

Data Index: 938332 (C4 (Web Text))

Max Activating Token Index: 15

Text #10

Max Range: 1.3876. Min Range: -1.3876

Max Act: 1.0435. Min Act: -0.0001

Data Index: 1256019 (C4 (Web Text))

Max Activating Token Index: 1013

Text #11

Max Range: 1.3876. Min Range: -1.3876

Max Act: 1.1114. Min Act: -0.0001

Data Index: 821210 (C4 (Web Text))

Max Activating Token Index: 22

Text #12

Max Range: 1.3876. Min Range: -1.3876

Max Act: 1.0587. Min Act: -0.0001

Data Index: 1218024 (C4 (Web Text))

Max Activating Token Index: 626

Text #13

Max Range: 1.3876. Min Range: -1.3876

Max Act: 1.0805. Min Act: -0.0001

Data Index: 223982 (C4 (Web Text))

Max Activating Token Index: 268

Text #14

Max Range: 1.3876. Min Range: -1.3876

Max Act: 0.9867. Min Act: -0.0001

Data Index: 187470 (C4 (Web Text))

Max Activating Token Index: 976

Text #15

Max Range: 1.3876. Min Range: -1.3876

Max Act: 1.0409. Min Act: -0.0001

Data Index: 289299 (C4 (Web Text))

Max Activating Token Index: 96

Text #16

Max Range: 1.3876. Min Range: -1.3876

Max Act: 0.9398. Min Act: -0.0001

Data Index: 528652 (C4 (Web Text))

Max Activating Token Index: 421

Text #17

Max Range: 1.3876. Min Range: -1.3876

Max Act: 0.9966. Min Act: -0.0001

Data Index: 252524 (C4 (Web Text))

Max Activating Token Index: 801

Text #18

Max Range: 1.3876. Min Range: -1.3876

Max Act: 1.0045. Min Act: -0.0001

Data Index: 1335679 (C4 (Web Text))

Max Activating Token Index: 567

Text #19

Max Range: 1.3876. Min Range: -1.3876

Max Act: 0.9663. Min Act: -0.0001

Data Index: 438249 (C4 (Web Text))

Max Activating Token Index: 874