Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1154 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1096. Min Range: -0.1096

Max Act: 0.1096. Min Act: -0.0005

Data Index: 715297 (C4 (Web Text))

Max Activating Token Index: 587

Text #1

Max Range: 0.1096. Min Range: -0.1096

Max Act: 0.1087. Min Act: -0.0005

Data Index: 881729 (C4 (Web Text))

Max Activating Token Index: 613

Text #2

Max Range: 0.1096. Min Range: -0.1096

Max Act: 0.1028. Min Act: -0.0005

Data Index: 32638 (C4 (Web Text))

Max Activating Token Index: 392

Text #3

Max Range: 0.1096. Min Range: -0.1096

Max Act: 0.1048. Min Act: -0.0005

Data Index: 43761 (C4 (Web Text))

Max Activating Token Index: 718

Text #4

Max Range: 0.1096. Min Range: -0.1096

Max Act: 0.0963. Min Act: -0.0005

Data Index: 299503 (C4 (Web Text))

Max Activating Token Index: 627

Text #5

Max Range: 0.1096. Min Range: -0.1096

Max Act: 0.1036. Min Act: -0.0005

Data Index: 359879 (C4 (Web Text))

Max Activating Token Index: 508

Text #6

Max Range: 0.1096. Min Range: -0.1096

Max Act: 0.1008. Min Act: -0.0005

Data Index: 504884 (C4 (Web Text))

Max Activating Token Index: 552

Text #7

Max Range: 0.1096. Min Range: -0.1096

Max Act: 0.0971. Min Act: -0.0005

Data Index: 800626 (C4 (Web Text))

Max Activating Token Index: 292

Text #8

Max Range: 0.1096. Min Range: -0.1096

Max Act: 0.0999. Min Act: -0.0005

Data Index: 500449 (C4 (Web Text))

Max Activating Token Index: 889

Text #9

Max Range: 0.1096. Min Range: -0.1096

Max Act: 0.0954. Min Act: -0.0005

Data Index: 788000 (C4 (Web Text))

Max Activating Token Index: 642

Text #10

Max Range: 0.1096. Min Range: -0.1096

Max Act: 0.1028. Min Act: -0.0005

Data Index: 785975 (C4 (Web Text))

Max Activating Token Index: 579

Text #11

Max Range: 0.1096. Min Range: -0.1096

Max Act: 0.0985. Min Act: -0.0005

Data Index: 385465 (C4 (Web Text))

Max Activating Token Index: 439

Text #12

Max Range: 0.1096. Min Range: -0.1096

Max Act: 0.1042. Min Act: -0.0005

Data Index: 738701 (C4 (Web Text))

Max Activating Token Index: 539

Text #13

Max Range: 0.1096. Min Range: -0.1096

Max Act: 0.0968. Min Act: -0.0005

Data Index: 353090 (C4 (Web Text))

Max Activating Token Index: 410

Text #14

Max Range: 0.1096. Min Range: -0.1096

Max Act: 0.0942. Min Act: -0.0005

Data Index: 1357058 (C4 (Web Text))

Max Activating Token Index: 290

Text #15

Max Range: 0.1096. Min Range: -0.1096

Max Act: 0.0998. Min Act: -0.0005

Data Index: 1258982 (C4 (Web Text))

Max Activating Token Index: 375

Text #16

Max Range: 0.1096. Min Range: -0.1096

Max Act: 0.0999. Min Act: -0.0005

Data Index: 218677 (C4 (Web Text))

Max Activating Token Index: 292

Text #17

Max Range: 0.1096. Min Range: -0.1096

Max Act: 0.0958. Min Act: -0.0005

Data Index: 515159 (C4 (Web Text))

Max Activating Token Index: 731

Text #18

Max Range: 0.1096. Min Range: -0.1096

Max Act: 0.0991. Min Act: -0.0005

Data Index: 399674 (C4 (Web Text))

Max Activating Token Index: 392

Text #19

Max Range: 0.1096. Min Range: -0.1096

Max Act: 0.0950. Min Act: -0.0005

Data Index: 1088417 (C4 (Web Text))

Max Activating Token Index: 48