Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1195 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.0637. Min Range: -1.0637

Max Act: 1.0637. Min Act: -0.0001

Data Index: 982382 (C4 (Web Text))

Max Activating Token Index: 7

Text #1

Max Range: 1.0637. Min Range: -1.0637

Max Act: 0.9902. Min Act: -0.0001

Data Index: 68943 (C4 (Web Text))

Max Activating Token Index: 60

Text #2

Max Range: 1.0637. Min Range: -1.0637

Max Act: 1.0090. Min Act: -0.0001

Data Index: 318098 (C4 (Web Text))

Max Activating Token Index: 132

Text #3

Max Range: 1.0637. Min Range: -1.0637

Max Act: 0.9774. Min Act: -0.0001

Data Index: 49283 (C4 (Web Text))

Max Activating Token Index: 1014

Text #4

Max Range: 1.0637. Min Range: -1.0637

Max Act: 0.9962. Min Act: -0.0001

Data Index: 1099323 (C4 (Web Text))

Max Activating Token Index: 993

Text #5

Max Range: 1.0637. Min Range: -1.0637

Max Act: 0.9320. Min Act: -0.0001

Data Index: 1231915 (C4 (Web Text))

Max Activating Token Index: 981

Text #6

Max Range: 1.0637. Min Range: -1.0637

Max Act: 0.8622. Min Act: -0.0001

Data Index: 463701 (C4 (Web Text))

Max Activating Token Index: 907

Text #7

Max Range: 1.0637. Min Range: -1.0637

Max Act: 0.9031. Min Act: -0.0001

Data Index: 871086 (C4 (Web Text))

Max Activating Token Index: 496

Text #8

Max Range: 1.0637. Min Range: -1.0637

Max Act: 0.8707. Min Act: -0.0001

Data Index: 197142 (C4 (Web Text))

Max Activating Token Index: 114

Text #9

Max Range: 1.0637. Min Range: -1.0637

Max Act: 0.9285. Min Act: -0.0001

Data Index: 818402 (C4 (Web Text))

Max Activating Token Index: 708

Text #10

Max Range: 1.0637. Min Range: -1.0637

Max Act: 0.9471. Min Act: -0.0001

Data Index: 1147305 (C4 (Web Text))

Max Activating Token Index: 452

Text #11

Max Range: 1.0637. Min Range: -1.0637

Max Act: 0.9178. Min Act: -0.0001

Data Index: 121519 (C4 (Web Text))

Max Activating Token Index: 638

Text #12

Max Range: 1.0637. Min Range: -1.0637

Max Act: 0.8517. Min Act: -0.0001

Data Index: 284346 (C4 (Web Text))

Max Activating Token Index: 842

Text #13

Max Range: 1.0637. Min Range: -1.0637

Max Act: 0.8688. Min Act: -0.0001

Data Index: 1353772 (C4 (Web Text))

Max Activating Token Index: 696

Text #14

Max Range: 1.0637. Min Range: -1.0637

Max Act: 0.8642. Min Act: -0.0001

Data Index: 700708 (C4 (Web Text))

Max Activating Token Index: 427

Text #15

Max Range: 1.0637. Min Range: -1.0637

Max Act: 0.8333. Min Act: -0.0001

Data Index: 1201064 (C4 (Web Text))

Max Activating Token Index: 926

Text #16

Max Range: 1.0637. Min Range: -1.0637

Max Act: 0.8033. Min Act: -0.0001

Data Index: 779638 (C4 (Web Text))

Max Activating Token Index: 480

Text #17

Max Range: 1.0637. Min Range: -1.0637

Max Act: 0.8499. Min Act: -0.0001

Data Index: 470431 (C4 (Web Text))

Max Activating Token Index: 902

Text #18

Max Range: 1.0637. Min Range: -1.0637

Max Act: 0.8532. Min Act: -0.0001

Data Index: 1027249 (C4 (Web Text))

Max Activating Token Index: 22

Text #19

Max Range: 1.0637. Min Range: -1.0637

Max Act: 0.8464. Min Act: -0.0001

Data Index: 517213 (C4 (Web Text))

Max Activating Token Index: 460