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

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

Neuron 5534 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: 1.6988. Min Range: -1.6988

Max Act: 1.6988. Min Act: -0.0000

Data Index: 12632 (C4 (Web Text))

Max Activating Token Index: 732

Text #1

Max Range: 1.6988. Min Range: -1.6988

Max Act: 1.4560. Min Act: -0.0000

Data Index: 284530 (C4 (Web Text))

Max Activating Token Index: 561

Text #2

Max Range: 1.6988. Min Range: -1.6988

Max Act: 1.3460. Min Act: -0.0000

Data Index: 1048256 (C4 (Web Text))

Max Activating Token Index: 240

Text #3

Max Range: 1.6988. Min Range: -1.6988

Max Act: 1.2722. Min Act: -0.0000

Data Index: 664269 (C4 (Web Text))

Max Activating Token Index: 955

Text #4

Max Range: 1.6988. Min Range: -1.6988

Max Act: 1.1615. Min Act: -0.0000

Data Index: 900750 (C4 (Web Text))

Max Activating Token Index: 685

Text #5

Max Range: 1.6988. Min Range: -1.6988

Max Act: 1.2545. Min Act: -0.0000

Data Index: 8954 (C4 (Web Text))

Max Activating Token Index: 820

Text #6

Max Range: 1.6988. Min Range: -1.6988

Max Act: 1.1637. Min Act: -0.0000

Data Index: 389760 (C4 (Web Text))

Max Activating Token Index: 960

Text #7

Max Range: 1.6988. Min Range: -1.6988

Max Act: 1.1323. Min Act: -0.0000

Data Index: 1192456 (C4 (Web Text))

Max Activating Token Index: 795

Text #8

Max Range: 1.6988. Min Range: -1.6988

Max Act: 1.1031. Min Act: -0.0000

Data Index: 1126777 (C4 (Web Text))

Max Activating Token Index: 912

Text #9

Max Range: 1.6988. Min Range: -1.6988

Max Act: 1.1101. Min Act: -0.0000

Data Index: 612642 (C4 (Web Text))

Max Activating Token Index: 599

Text #10

Max Range: 1.6988. Min Range: -1.6988

Max Act: 1.0589. Min Act: -0.0000

Data Index: 536032 (C4 (Web Text))

Max Activating Token Index: 229

Text #11

Max Range: 1.6988. Min Range: -1.6988

Max Act: 1.1074. Min Act: -0.0000

Data Index: 791018 (C4 (Web Text))

Max Activating Token Index: 384

Text #12

Max Range: 1.6988. Min Range: -1.6988

Max Act: 1.0849. Min Act: -0.0000

Data Index: 247171 (C4 (Web Text))

Max Activating Token Index: 587

Text #13

Max Range: 1.6988. Min Range: -1.6988

Max Act: 1.0806. Min Act: -0.0000

Data Index: 324443 (C4 (Web Text))

Max Activating Token Index: 1016

Text #14

Max Range: 1.6988. Min Range: -1.6988

Max Act: 1.0725. Min Act: -0.0000

Data Index: 745198 (C4 (Web Text))

Max Activating Token Index: 512

Text #15

Max Range: 1.6988. Min Range: -1.6988

Max Act: 1.0097. Min Act: 0.0000

Data Index: 233211 (C4 (Web Text))

Max Activating Token Index: 596

Text #16

Max Range: 1.6988. Min Range: -1.6988

Max Act: 1.0022. Min Act: -0.0000

Data Index: 45325 (C4 (Web Text))

Max Activating Token Index: 741

Text #17

Max Range: 1.6988. Min Range: -1.6988

Max Act: 1.0664. Min Act: -0.0000

Data Index: 894522 (C4 (Web Text))

Max Activating Token Index: 295

Text #18

Max Range: 1.6988. Min Range: -1.6988

Max Act: 0.9968. Min Act: -0.0000

Data Index: 609423 (C4 (Web Text))

Max Activating Token Index: 878

Text #19

Max Range: 1.6988. Min Range: -1.6988

Max Act: 0.9932. Min Act: -0.0000

Data Index: 411022 (C4 (Web Text))

Max Activating Token Index: 36