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

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

Neuron 4646 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.1065. Min Range: -0.1065

Max Act: 0.1065. Min Act: -0.0002

Data Index: 444257 (C4 (Web Text))

Max Activating Token Index: 717

Text #1

Max Range: 0.1065. Min Range: -0.1065

Max Act: 0.1028. Min Act: -0.0002

Data Index: 797210 (C4 (Web Text))

Max Activating Token Index: 808

Text #2

Max Range: 0.1065. Min Range: -0.1065

Max Act: 0.1025. Min Act: -0.0002

Data Index: 76938 (C4 (Web Text))

Max Activating Token Index: 20

Text #3

Max Range: 0.1065. Min Range: -0.1065

Max Act: 0.1013. Min Act: -0.0002

Data Index: 1047501 (C4 (Web Text))

Max Activating Token Index: 746

Text #4

Max Range: 0.1065. Min Range: -0.1065

Max Act: 0.1020. Min Act: -0.0002

Data Index: 548039 (C4 (Web Text))

Max Activating Token Index: 719

Text #5

Max Range: 0.1065. Min Range: -0.1065

Max Act: 0.1027. Min Act: -0.0002

Data Index: 355994 (C4 (Web Text))

Max Activating Token Index: 880

Text #6

Max Range: 0.1065. Min Range: -0.1065

Max Act: 0.1011. Min Act: -0.0002

Data Index: 1344401 (C4 (Web Text))

Max Activating Token Index: 769

Text #7

Max Range: 0.1065. Min Range: -0.1065

Max Act: 0.1034. Min Act: -0.0002

Data Index: 725537 (C4 (Web Text))

Max Activating Token Index: 535

Text #8

Max Range: 0.1065. Min Range: -0.1065

Max Act: 0.1001. Min Act: -0.0002

Data Index: 578726 (C4 (Web Text))

Max Activating Token Index: 737

Text #9

Max Range: 0.1065. Min Range: -0.1065

Max Act: 0.1019. Min Act: -0.0002

Data Index: 507234 (C4 (Web Text))

Max Activating Token Index: 1013

Text #10

Max Range: 0.1065. Min Range: -0.1065

Max Act: 0.1030. Min Act: -0.0002

Data Index: 231150 (C4 (Web Text))

Max Activating Token Index: 826

Text #11

Max Range: 0.1065. Min Range: -0.1065

Max Act: 0.1018. Min Act: -0.0002

Data Index: 908758 (C4 (Web Text))

Max Activating Token Index: 752

Text #12

Max Range: 0.1065. Min Range: -0.1065

Max Act: 0.1022. Min Act: -0.0002

Data Index: 1065558 (C4 (Web Text))

Max Activating Token Index: 556

Text #13

Max Range: 0.1065. Min Range: -0.1065

Max Act: 0.1013. Min Act: -0.0002

Data Index: 768656 (C4 (Web Text))

Max Activating Token Index: 926

Text #14

Max Range: 0.1065. Min Range: -0.1065

Max Act: 0.1005. Min Act: -0.0002

Data Index: 268662 (C4 (Web Text))

Max Activating Token Index: 467

Text #15

Max Range: 0.1065. Min Range: -0.1065

Max Act: 0.0982. Min Act: -0.0002

Data Index: 480118 (C4 (Web Text))

Max Activating Token Index: 886

Text #16

Max Range: 0.1065. Min Range: -0.1065

Max Act: 0.0994. Min Act: -0.0002

Data Index: 1333235 (C4 (Web Text))

Max Activating Token Index: 988

Text #17

Max Range: 0.1065. Min Range: -0.1065

Max Act: 0.0982. Min Act: -0.0002

Data Index: 1167644 (C4 (Web Text))

Max Activating Token Index: 620

Text #18

Max Range: 0.1065. Min Range: -0.1065

Max Act: 0.0978. Min Act: -0.0002

Data Index: 1276915 (C4 (Web Text))

Max Activating Token Index: 52

Text #19

Max Range: 0.1065. Min Range: -0.1065

Max Act: 0.0990. Min Act: -0.0002

Data Index: 685240 (C4 (Web Text))

Max Activating Token Index: 725