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

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

Neuron 4539 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8348. Min Range: -0.8348

Max Act: 0.8030. Min Act: -0.0000

Data Index: 762722 (C4 (Web Text))

Max Activating Token Index: 948

Text #1

Max Range: 0.8348. Min Range: -0.8348

Max Act: 0.8083. Min Act: -0.0000

Data Index: 588200 (C4 (Web Text))

Max Activating Token Index: 1014

Text #2

Max Range: 0.8348. Min Range: -0.8348

Max Act: 0.8348. Min Act: -0.0000

Data Index: 1230988 (C4 (Web Text))

Max Activating Token Index: 192

Text #3

Max Range: 0.8348. Min Range: -0.8348

Max Act: 0.7074. Min Act: -0.0000

Data Index: 72211 (C4 (Web Text))

Max Activating Token Index: 973

Text #4

Max Range: 0.8348. Min Range: -0.8348

Max Act: 0.7728. Min Act: -0.0000

Data Index: 1209108 (C4 (Web Text))

Max Activating Token Index: 778

Text #5

Max Range: 0.8348. Min Range: -0.8348

Max Act: 0.7493. Min Act: -0.0000

Data Index: 699126 (C4 (Web Text))

Max Activating Token Index: 332

Text #6

Max Range: 0.8348. Min Range: -0.8348

Max Act: 0.7437. Min Act: -0.0000

Data Index: 757600 (C4 (Web Text))

Max Activating Token Index: 51

Text #7

Max Range: 0.8348. Min Range: -0.8348

Max Act: 0.7372. Min Act: -0.0000

Data Index: 842015 (C4 (Web Text))

Max Activating Token Index: 443

Text #8

Max Range: 0.8348. Min Range: -0.8348

Max Act: 0.6970. Min Act: -0.0000

Data Index: 1252947 (C4 (Web Text))

Max Activating Token Index: 677

Text #9

Max Range: 0.8348. Min Range: -0.8348

Max Act: 0.5955. Min Act: -0.0000

Data Index: 42198 (C4 (Web Text))

Max Activating Token Index: 904

Text #10

Max Range: 0.8348. Min Range: -0.8348

Max Act: 0.6884. Min Act: -0.0000

Data Index: 1176578 (C4 (Web Text))

Max Activating Token Index: 109

Text #11

Max Range: 0.8348. Min Range: -0.8348

Max Act: 0.6847. Min Act: -0.0000

Data Index: 548600 (C4 (Web Text))

Max Activating Token Index: 898

Text #12

Max Range: 0.8348. Min Range: -0.8348

Max Act: 0.6841. Min Act: -0.0000

Data Index: 1096202 (C4 (Web Text))

Max Activating Token Index: 660

Text #13

Max Range: 0.8348. Min Range: -0.8348

Max Act: 0.6612. Min Act: -0.0000

Data Index: 634904 (C4 (Web Text))

Max Activating Token Index: 500

Text #14

Max Range: 0.8348. Min Range: -0.8348

Max Act: 0.6472. Min Act: -0.0000

Data Index: 460865 (C4 (Web Text))

Max Activating Token Index: 932

Text #15

Max Range: 0.8348. Min Range: -0.8348

Max Act: 0.7848. Min Act: -0.0000

Data Index: 606621 (C4 (Web Text))

Max Activating Token Index: 595

Text #16

Max Range: 0.8348. Min Range: -0.8348

Max Act: 0.6950. Min Act: -0.0000

Data Index: 54839 (C4 (Web Text))

Max Activating Token Index: 848

Text #17

Max Range: 0.8348. Min Range: -0.8348

Max Act: 0.6321. Min Act: -0.0000

Data Index: 118312 (C4 (Web Text))

Max Activating Token Index: 788

Text #18

Max Range: 0.8348. Min Range: -0.8348

Max Act: 0.6590. Min Act: -0.0000

Data Index: 883774 (C4 (Web Text))

Max Activating Token Index: 436

Text #19

Max Range: 0.8348. Min Range: -0.8348

Max Act: 0.6999. Min Act: -0.0000

Data Index: 200426 (C4 (Web Text))

Max Activating Token Index: 156