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

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

Neuron 2425 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3603. Min Range: -1.3603

Max Act: 1.3603. Min Act: 0.0000

Data Index: 431502 (C4 (Web Text))

Max Activating Token Index: 302

Text #1

Max Range: 1.3603. Min Range: -1.3603

Max Act: 1.1939. Min Act: -0.0000

Data Index: 865623 (C4 (Web Text))

Max Activating Token Index: 597

Text #2

Max Range: 1.3603. Min Range: -1.3603

Max Act: 1.2327. Min Act: 0.0001

Data Index: 159704 (C4 (Web Text))

Max Activating Token Index: 994

Text #3

Max Range: 1.3603. Min Range: -1.3603

Max Act: 1.0988. Min Act: 0.0001

Data Index: 412967 (C4 (Web Text))

Max Activating Token Index: 320

Text #4

Max Range: 1.3603. Min Range: -1.3603

Max Act: 1.1076. Min Act: -0.0000

Data Index: 397668 (C4 (Web Text))

Max Activating Token Index: 639

Text #5

Max Range: 1.3603. Min Range: -1.3603

Max Act: 1.1005. Min Act: 0.0000

Data Index: 262091 (C4 (Web Text))

Max Activating Token Index: 523

Text #6

Max Range: 1.3603. Min Range: -1.3603

Max Act: 1.1521. Min Act: -0.0000

Data Index: 1175284 (C4 (Web Text))

Max Activating Token Index: 606

Text #7

Max Range: 1.3603. Min Range: -1.3603

Max Act: 1.0780. Min Act: -0.0000

Data Index: 749337 (C4 (Web Text))

Max Activating Token Index: 438

Text #8

Max Range: 1.3603. Min Range: -1.3603

Max Act: 1.1158. Min Act: -0.0000

Data Index: 787496 (C4 (Web Text))

Max Activating Token Index: 214

Text #9

Max Range: 1.3603. Min Range: -1.3603

Max Act: 1.0700. Min Act: 0.0000

Data Index: 152687 (C4 (Web Text))

Max Activating Token Index: 11

Text #10

Max Range: 1.3603. Min Range: -1.3603

Max Act: 0.9598. Min Act: -0.0000

Data Index: 1232554 (C4 (Web Text))

Max Activating Token Index: 255

Text #11

Max Range: 1.3603. Min Range: -1.3603

Max Act: 0.8552. Min Act: -0.0000

Data Index: 1357604 (C4 (Web Text))

Max Activating Token Index: 46

Text #12

Max Range: 1.3603. Min Range: -1.3603

Max Act: 0.9220. Min Act: -0.0000

Data Index: 1016332 (C4 (Web Text))

Max Activating Token Index: 307

Text #13

Max Range: 1.3603. Min Range: -1.3603

Max Act: 0.8851. Min Act: -0.0000

Data Index: 953078 (C4 (Web Text))

Max Activating Token Index: 401

Text #14

Max Range: 1.3603. Min Range: -1.3603

Max Act: 0.8719. Min Act: -0.0000

Data Index: 790103 (C4 (Web Text))

Max Activating Token Index: 942

Text #15

Max Range: 1.3603. Min Range: -1.3603

Max Act: 0.8776. Min Act: -0.0000

Data Index: 138649 (C4 (Web Text))

Max Activating Token Index: 302

Text #16

Max Range: 1.3603. Min Range: -1.3603

Max Act: 0.8447. Min Act: -0.0000

Data Index: 44138 (C4 (Web Text))

Max Activating Token Index: 60

Text #17

Max Range: 1.3603. Min Range: -1.3603

Max Act: 0.8300. Min Act: 0.0001

Data Index: 28099 (C4 (Web Text))

Max Activating Token Index: 132

Text #18

Max Range: 1.3603. Min Range: -1.3603

Max Act: 0.8011. Min Act: -0.0000

Data Index: 1342378 (C4 (Web Text))

Max Activating Token Index: 759

Text #19

Max Range: 1.3603. Min Range: -1.3603

Max Act: 0.8213. Min Act: 0.0001

Data Index: 738726 (C4 (Web Text))

Max Activating Token Index: 585