Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3874 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.3988. Min Range: -1.3988

Max Act: 1.3988. Min Act: -0.0000

Data Index: 757150 (C4 (Web Text))

Max Activating Token Index: 989

Text #1

Max Range: 1.3988. Min Range: -1.3988

Max Act: 1.1188. Min Act: -0.0000

Data Index: 7403 (C4 (Web Text))

Max Activating Token Index: 535

Text #2

Max Range: 1.3988. Min Range: -1.3988

Max Act: 1.1753. Min Act: -0.0000

Data Index: 972808 (C4 (Web Text))

Max Activating Token Index: 882

Text #3

Max Range: 1.3988. Min Range: -1.3988

Max Act: 1.2552. Min Act: -0.0000

Data Index: 851006 (C4 (Web Text))

Max Activating Token Index: 1013

Text #4

Max Range: 1.3988. Min Range: -1.3988

Max Act: 1.0658. Min Act: -0.0000

Data Index: 1228395 (C4 (Web Text))

Max Activating Token Index: 607

Text #5

Max Range: 1.3988. Min Range: -1.3988

Max Act: 1.1250. Min Act: -0.0000

Data Index: 60135 (C4 (Web Text))

Max Activating Token Index: 913

Text #6

Max Range: 1.3988. Min Range: -1.3988

Max Act: 1.0523. Min Act: -0.0000

Data Index: 985971 (C4 (Web Text))

Max Activating Token Index: 1021

Text #7

Max Range: 1.3988. Min Range: -1.3988

Max Act: 1.0413. Min Act: -0.0000

Data Index: 338868 (C4 (Web Text))

Max Activating Token Index: 796

Text #8

Max Range: 1.3988. Min Range: -1.3988

Max Act: 0.9489. Min Act: -0.0000

Data Index: 225389 (C4 (Web Text))

Max Activating Token Index: 506

Text #9

Max Range: 1.3988. Min Range: -1.3988

Max Act: 1.0556. Min Act: -0.0000

Data Index: 143142 (C4 (Web Text))

Max Activating Token Index: 985

Text #10

Max Range: 1.3988. Min Range: -1.3988

Max Act: 0.9133. Min Act: -0.0000

Data Index: 879674 (C4 (Web Text))

Max Activating Token Index: 721

Text #11

Max Range: 1.3988. Min Range: -1.3988

Max Act: 0.9669. Min Act: -0.0000

Data Index: 383491 (C4 (Web Text))

Max Activating Token Index: 672

Text #12

Max Range: 1.3988. Min Range: -1.3988

Max Act: 0.8942. Min Act: -0.0000

Data Index: 556335 (C4 (Web Text))

Max Activating Token Index: 89

Text #13

Max Range: 1.3988. Min Range: -1.3988

Max Act: 0.9069. Min Act: -0.0000

Data Index: 429008 (C4 (Web Text))

Max Activating Token Index: 956

Text #14

Max Range: 1.3988. Min Range: -1.3988

Max Act: 1.0151. Min Act: -0.0000

Data Index: 235818 (C4 (Web Text))

Max Activating Token Index: 944

Text #15

Max Range: 1.3988. Min Range: -1.3988

Max Act: 0.9667. Min Act: -0.0000

Data Index: 667405 (C4 (Web Text))

Max Activating Token Index: 119

Text #16

Max Range: 1.3988. Min Range: -1.3988

Max Act: 0.8207. Min Act: -0.0000

Data Index: 577678 (C4 (Web Text))

Max Activating Token Index: 866

Text #17

Max Range: 1.3988. Min Range: -1.3988

Max Act: 0.9166. Min Act: -0.0000

Data Index: 1087612 (C4 (Web Text))

Max Activating Token Index: 233

Text #18

Max Range: 1.3988. Min Range: -1.3988

Max Act: 0.8840. Min Act: -0.0000

Data Index: 1198879 (C4 (Web Text))

Max Activating Token Index: 532

Text #19

Max Range: 1.3988. Min Range: -1.3988

Max Act: 0.8246. Min Act: -0.0000

Data Index: 501728 (C4 (Web Text))

Max Activating Token Index: 989