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

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

Neuron 997 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3684. Min Range: -1.3684

Max Act: 1.3684. Min Act: -0.0000

Data Index: 948859 (C4 (Web Text))

Max Activating Token Index: 533

Text #1

Max Range: 1.3684. Min Range: -1.3684

Max Act: 1.2316. Min Act: -0.0000

Data Index: 490502 (C4 (Web Text))

Max Activating Token Index: 441

Text #2

Max Range: 1.3684. Min Range: -1.3684

Max Act: 1.1996. Min Act: -0.0000

Data Index: 831416 (C4 (Web Text))

Max Activating Token Index: 582

Text #3

Max Range: 1.3684. Min Range: -1.3684

Max Act: 1.2052. Min Act: -0.0000

Data Index: 1193338 (C4 (Web Text))

Max Activating Token Index: 420

Text #4

Max Range: 1.3684. Min Range: -1.3684

Max Act: 1.1875. Min Act: -0.0000

Data Index: 1040725 (C4 (Web Text))

Max Activating Token Index: 644

Text #5

Max Range: 1.3684. Min Range: -1.3684

Max Act: 1.0786. Min Act: -0.0000

Data Index: 866381 (C4 (Web Text))

Max Activating Token Index: 177

Text #6

Max Range: 1.3684. Min Range: -1.3684

Max Act: 1.0980. Min Act: -0.0000

Data Index: 770198 (C4 (Web Text))

Max Activating Token Index: 642

Text #7

Max Range: 1.3684. Min Range: -1.3684

Max Act: 1.0587. Min Act: -0.0000

Data Index: 657420 (C4 (Web Text))

Max Activating Token Index: 118

Text #8

Max Range: 1.3684. Min Range: -1.3684

Max Act: 1.0360. Min Act: -0.0000

Data Index: 345586 (C4 (Web Text))

Max Activating Token Index: 573

Text #9

Max Range: 1.3684. Min Range: -1.3684

Max Act: 0.9927. Min Act: -0.0000

Data Index: 1024110 (C4 (Web Text))

Max Activating Token Index: 999

Text #10

Max Range: 1.3684. Min Range: -1.3684

Max Act: 1.0015. Min Act: -0.0000

Data Index: 212674 (C4 (Web Text))

Max Activating Token Index: 610

Text #11

Max Range: 1.3684. Min Range: -1.3684

Max Act: 0.9317. Min Act: -0.0000

Data Index: 560578 (C4 (Web Text))

Max Activating Token Index: 782

Text #12

Max Range: 1.3684. Min Range: -1.3684

Max Act: 0.9883. Min Act: -0.0000

Data Index: 915088 (C4 (Web Text))

Max Activating Token Index: 175

Text #13

Max Range: 1.3684. Min Range: -1.3684

Max Act: 0.9762. Min Act: -0.0000

Data Index: 1033296 (C4 (Web Text))

Max Activating Token Index: 60

Text #14

Max Range: 1.3684. Min Range: -1.3684

Max Act: 0.9912. Min Act: -0.0000

Data Index: 1175066 (C4 (Web Text))

Max Activating Token Index: 293

Text #15

Max Range: 1.3684. Min Range: -1.3684

Max Act: 0.9930. Min Act: -0.0000

Data Index: 337421 (C4 (Web Text))

Max Activating Token Index: 761

Text #16

Max Range: 1.3684. Min Range: -1.3684

Max Act: 0.9498. Min Act: -0.0000

Data Index: 1330380 (C4 (Web Text))

Max Activating Token Index: 921

Text #17

Max Range: 1.3684. Min Range: -1.3684

Max Act: 0.9443. Min Act: -0.0000

Data Index: 361584 (C4 (Web Text))

Max Activating Token Index: 817

Text #18

Max Range: 1.3684. Min Range: -1.3684

Max Act: 0.8735. Min Act: -0.0000

Data Index: 1108923 (C4 (Web Text))

Max Activating Token Index: 944

Text #19

Max Range: 1.3684. Min Range: -1.3684

Max Act: 0.9060. Min Act: -0.0000

Data Index: 751101 (C4 (Web Text))

Max Activating Token Index: 585