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

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

Neuron 3370 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: 0.9993. Min Range: -0.9993

Max Act: 0.9993. Min Act: -0.0000

Data Index: 622499 (C4 (Web Text))

Max Activating Token Index: 891

Text #1

Max Range: 0.9993. Min Range: -0.9993

Max Act: 0.9027. Min Act: -0.0000

Data Index: 881594 (C4 (Web Text))

Max Activating Token Index: 989

Text #2

Max Range: 0.9993. Min Range: -0.9993

Max Act: 0.9026. Min Act: -0.0000

Data Index: 1326236 (C4 (Web Text))

Max Activating Token Index: 898

Text #3

Max Range: 0.9993. Min Range: -0.9993

Max Act: 0.8377. Min Act: -0.0000

Data Index: 626961 (C4 (Web Text))

Max Activating Token Index: 893

Text #4

Max Range: 0.9993. Min Range: -0.9993

Max Act: 0.6958. Min Act: -0.0000

Data Index: 595071 (C4 (Web Text))

Max Activating Token Index: 717

Text #5

Max Range: 0.9993. Min Range: -0.9993

Max Act: 0.7497. Min Act: -0.0000

Data Index: 558018 (C4 (Web Text))

Max Activating Token Index: 337

Text #6

Max Range: 0.9993. Min Range: -0.9993

Max Act: 0.7457. Min Act: -0.0000

Data Index: 1264172 (C4 (Web Text))

Max Activating Token Index: 18

Text #7

Max Range: 0.9993. Min Range: -0.9993

Max Act: 0.7197. Min Act: -0.0000

Data Index: 583848 (C4 (Web Text))

Max Activating Token Index: 990

Text #8

Max Range: 0.9993. Min Range: -0.9993

Max Act: 0.6750. Min Act: -0.0000

Data Index: 1287796 (C4 (Web Text))

Max Activating Token Index: 491

Text #9

Max Range: 0.9993. Min Range: -0.9993

Max Act: 0.7124. Min Act: -0.0000

Data Index: 1169897 (C4 (Web Text))

Max Activating Token Index: 626

Text #10

Max Range: 0.9993. Min Range: -0.9993

Max Act: 0.7375. Min Act: -0.0000

Data Index: 413285 (C4 (Web Text))

Max Activating Token Index: 85

Text #11

Max Range: 0.9993. Min Range: -0.9993

Max Act: 0.7535. Min Act: -0.0000

Data Index: 954778 (C4 (Web Text))

Max Activating Token Index: 900

Text #12

Max Range: 0.9993. Min Range: -0.9993

Max Act: 0.6699. Min Act: -0.0000

Data Index: 106770 (C4 (Web Text))

Max Activating Token Index: 352

Text #13

Max Range: 0.9993. Min Range: -0.9993

Max Act: 0.7560. Min Act: -0.0000

Data Index: 776660 (C4 (Web Text))

Max Activating Token Index: 903

Text #14

Max Range: 0.9993. Min Range: -0.9993

Max Act: 0.7031. Min Act: -0.0000

Data Index: 622421 (C4 (Web Text))

Max Activating Token Index: 632

Text #15

Max Range: 0.9993. Min Range: -0.9993

Max Act: 0.7015. Min Act: -0.0000

Data Index: 256733 (C4 (Web Text))

Max Activating Token Index: 941

Text #16

Max Range: 0.9993. Min Range: -0.9993

Max Act: 0.7034. Min Act: -0.0000

Data Index: 592323 (C4 (Web Text))

Max Activating Token Index: 651

Text #17

Max Range: 0.9993. Min Range: -0.9993

Max Act: 0.6675. Min Act: -0.0000

Data Index: 690121 (C4 (Web Text))

Max Activating Token Index: 97

Text #18

Max Range: 0.9993. Min Range: -0.9993

Max Act: 0.6180. Min Act: -0.0000

Data Index: 325247 (C4 (Web Text))

Max Activating Token Index: 105

Text #19

Max Range: 0.9993. Min Range: -0.9993

Max Act: 0.5901. Min Act: -0.0000

Data Index: 505530 (C4 (Web Text))

Max Activating Token Index: 121