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

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

Neuron 1673 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.0886. Min Range: -4.0886

Max Act: 4.0886. Min Act: -0.0000

Data Index: 103810 (C4 (Web Text))

Max Activating Token Index: 637

Text #1

Max Range: 4.0886. Min Range: -4.0886

Max Act: 3.6796. Min Act: -0.0000

Data Index: 71803 (C4 (Web Text))

Max Activating Token Index: 612

Text #2

Max Range: 4.0886. Min Range: -4.0886

Max Act: 3.5333. Min Act: -0.0000

Data Index: 722686 (C4 (Web Text))

Max Activating Token Index: 367

Text #3

Max Range: 4.0886. Min Range: -4.0886

Max Act: 3.1290. Min Act: -0.0000

Data Index: 838855 (C4 (Web Text))

Max Activating Token Index: 591

Text #4

Max Range: 4.0886. Min Range: -4.0886

Max Act: 3.2720. Min Act: -0.0000

Data Index: 1181713 (C4 (Web Text))

Max Activating Token Index: 1012

Text #5

Max Range: 4.0886. Min Range: -4.0886

Max Act: 3.0377. Min Act: -0.0000

Data Index: 1351537 (C4 (Web Text))

Max Activating Token Index: 309

Text #6

Max Range: 4.0886. Min Range: -4.0886

Max Act: 3.1849. Min Act: -0.0000

Data Index: 451085 (C4 (Web Text))

Max Activating Token Index: 36

Text #7

Max Range: 4.0886. Min Range: -4.0886

Max Act: 2.9360. Min Act: -0.0000

Data Index: 657657 (C4 (Web Text))

Max Activating Token Index: 1013

Text #8

Max Range: 4.0886. Min Range: -4.0886

Max Act: 3.2059. Min Act: -0.0000

Data Index: 687676 (C4 (Web Text))

Max Activating Token Index: 148

Text #9

Max Range: 4.0886. Min Range: -4.0886

Max Act: 3.0357. Min Act: -0.0000

Data Index: 1036329 (C4 (Web Text))

Max Activating Token Index: 393

Text #10

Max Range: 4.0886. Min Range: -4.0886

Max Act: 2.9652. Min Act: -0.0000

Data Index: 203195 (C4 (Web Text))

Max Activating Token Index: 802

Text #11

Max Range: 4.0886. Min Range: -4.0886

Max Act: 3.1198. Min Act: -0.0000

Data Index: 89339 (C4 (Web Text))

Max Activating Token Index: 873

Text #12

Max Range: 4.0886. Min Range: -4.0886

Max Act: 2.9609. Min Act: -0.0000

Data Index: 719096 (C4 (Web Text))

Max Activating Token Index: 724

Text #13

Max Range: 4.0886. Min Range: -4.0886

Max Act: 2.9422. Min Act: -0.0000

Data Index: 29250 (C4 (Web Text))

Max Activating Token Index: 207

Text #14

Max Range: 4.0886. Min Range: -4.0886

Max Act: 2.9141. Min Act: -0.0000

Data Index: 139325 (C4 (Web Text))

Max Activating Token Index: 923

Text #15

Max Range: 4.0886. Min Range: -4.0886

Max Act: 2.7527. Min Act: -0.0000

Data Index: 986221 (C4 (Web Text))

Max Activating Token Index: 637

Text #16

Max Range: 4.0886. Min Range: -4.0886

Max Act: 2.7071. Min Act: -0.0000

Data Index: 595256 (C4 (Web Text))

Max Activating Token Index: 565

Text #17

Max Range: 4.0886. Min Range: -4.0886

Max Act: 2.7897. Min Act: -0.0000

Data Index: 1099923 (C4 (Web Text))

Max Activating Token Index: 596

Text #18

Max Range: 4.0886. Min Range: -4.0886

Max Act: 2.7582. Min Act: -0.0000

Data Index: 645716 (C4 (Web Text))

Max Activating Token Index: 1010

Text #19

Max Range: 4.0886. Min Range: -4.0886

Max Act: 2.7399. Min Act: -0.0000

Data Index: 1111865 (C4 (Web Text))

Max Activating Token Index: 606