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

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

Neuron 3042 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0904. Min Act: -0.0000

Data Index: 887227 (C4 (Web Text))

Max Activating Token Index: 291

Text #1

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0905. Min Act: -0.0000

Data Index: 442646 (C4 (Web Text))

Max Activating Token Index: 36

Text #2

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0934. Min Act: -0.0000

Data Index: 394140 (C4 (Web Text))

Max Activating Token Index: 473

Text #3

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0892. Min Act: -0.0000

Data Index: 1197143 (C4 (Web Text))

Max Activating Token Index: 28

Text #4

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0810. Min Act: -0.0000

Data Index: 1154006 (C4 (Web Text))

Max Activating Token Index: 161

Text #5

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0933. Min Act: -0.0000

Data Index: 28247 (C4 (Web Text))

Max Activating Token Index: 870

Text #6

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0838. Min Act: -0.0000

Data Index: 1122571 (C4 (Web Text))

Max Activating Token Index: 773

Text #7

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0780. Min Act: -0.0000

Data Index: 828866 (C4 (Web Text))

Max Activating Token Index: 112

Text #8

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0772. Min Act: -0.0000

Data Index: 1034237 (C4 (Web Text))

Max Activating Token Index: 494

Text #9

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0738. Min Act: -0.0000

Data Index: 576327 (C4 (Web Text))

Max Activating Token Index: 469

Text #10

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0699. Min Act: -0.0000

Data Index: 13134 (C4 (Web Text))

Max Activating Token Index: 182

Text #11

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0751. Min Act: -0.0000

Data Index: 511330 (C4 (Web Text))

Max Activating Token Index: 329

Text #12

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0691. Min Act: -0.0000

Data Index: 252759 (C4 (Web Text))

Max Activating Token Index: 642

Text #13

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0630. Min Act: -0.0000

Data Index: 787256 (C4 (Web Text))

Max Activating Token Index: 852

Text #14

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0754. Min Act: -0.0000

Data Index: 154946 (C4 (Web Text))

Max Activating Token Index: 937

Text #15

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0663. Min Act: -0.0000

Data Index: 278160 (C4 (Web Text))

Max Activating Token Index: 189

Text #16

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0731. Min Act: -0.0000

Data Index: 150101 (C4 (Web Text))

Max Activating Token Index: 324

Text #17

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0675. Min Act: -0.0000

Data Index: 949289 (C4 (Web Text))

Max Activating Token Index: 166

Text #18

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0645. Min Act: -0.0000

Data Index: 724685 (C4 (Web Text))

Max Activating Token Index: 465

Text #19

Max Range: 0.0934. Min Range: -0.0934

Max Act: 0.0621. Min Act: -0.0000

Data Index: 1257168 (C4 (Web Text))

Max Activating Token Index: 274