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

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

Neuron 50 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: 3.9266. Min Range: -3.9266

Max Act: 3.7994. Min Act: -0.0000

Data Index: 684072 (C4 (Web Text))

Max Activating Token Index: 289

Text #1

Max Range: 3.9266. Min Range: -3.9266

Max Act: 3.9266. Min Act: -0.0000

Data Index: 429824 (C4 (Web Text))

Max Activating Token Index: 857

Text #2

Max Range: 3.9266. Min Range: -3.9266

Max Act: 3.4746. Min Act: -0.0000

Data Index: 282425 (C4 (Web Text))

Max Activating Token Index: 991

Text #3

Max Range: 3.9266. Min Range: -3.9266

Max Act: 3.1050. Min Act: -0.0000

Data Index: 1042826 (C4 (Web Text))

Max Activating Token Index: 695

Text #4

Max Range: 3.9266. Min Range: -3.9266

Max Act: 2.8589. Min Act: -0.0000

Data Index: 220821 (C4 (Web Text))

Max Activating Token Index: 334

Text #5

Max Range: 3.9266. Min Range: -3.9266

Max Act: 2.8292. Min Act: -0.0000

Data Index: 1265616 (C4 (Web Text))

Max Activating Token Index: 746

Text #6

Max Range: 3.9266. Min Range: -3.9266

Max Act: 2.7786. Min Act: -0.0000

Data Index: 3589 (C4 (Web Text))

Max Activating Token Index: 132

Text #7

Max Range: 3.9266. Min Range: -3.9266

Max Act: 2.7327. Min Act: -0.0000

Data Index: 355195 (C4 (Web Text))

Max Activating Token Index: 107

Text #8

Max Range: 3.9266. Min Range: -3.9266

Max Act: 2.8480. Min Act: -0.0000

Data Index: 440293 (C4 (Web Text))

Max Activating Token Index: 351

Text #9

Max Range: 3.9266. Min Range: -3.9266

Max Act: 2.7082. Min Act: -0.0000

Data Index: 827891 (C4 (Web Text))

Max Activating Token Index: 926

Text #10

Max Range: 3.9266. Min Range: -3.9266

Max Act: 2.5489. Min Act: -0.0000

Data Index: 815019 (C4 (Web Text))

Max Activating Token Index: 25

Text #11

Max Range: 3.9266. Min Range: -3.9266

Max Act: 2.3001. Min Act: -0.0000

Data Index: 674541 (C4 (Web Text))

Max Activating Token Index: 81

Text #12

Max Range: 3.9266. Min Range: -3.9266

Max Act: 2.2472. Min Act: -0.0000

Data Index: 1029499 (C4 (Web Text))

Max Activating Token Index: 845

Text #13

Max Range: 3.9266. Min Range: -3.9266

Max Act: 2.3399. Min Act: -0.0000

Data Index: 969555 (C4 (Web Text))

Max Activating Token Index: 468

Text #14

Max Range: 3.9266. Min Range: -3.9266

Max Act: 2.1333. Min Act: -0.0000

Data Index: 423074 (C4 (Web Text))

Max Activating Token Index: 739

Text #15

Max Range: 3.9266. Min Range: -3.9266

Max Act: 2.0107. Min Act: -0.0000

Data Index: 1053860 (C4 (Web Text))

Max Activating Token Index: 755

Text #16

Max Range: 3.9266. Min Range: -3.9266

Max Act: 2.1896. Min Act: -0.0000

Data Index: 819024 (C4 (Web Text))

Max Activating Token Index: 203

Text #17

Max Range: 3.9266. Min Range: -3.9266

Max Act: 1.8657. Min Act: -0.0000

Data Index: 640759 (C4 (Web Text))

Max Activating Token Index: 738

Text #18

Max Range: 3.9266. Min Range: -3.9266

Max Act: 1.9758. Min Act: -0.0000

Data Index: 1201070 (C4 (Web Text))

Max Activating Token Index: 924

Text #19

Max Range: 3.9266. Min Range: -3.9266

Max Act: 1.9562. Min Act: -0.0000

Data Index: 172160 (C4 (Web Text))

Max Activating Token Index: 670