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

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

Neuron 3707 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7075. Min Range: -0.7075

Max Act: 0.7075. Min Act: -0.0000

Data Index: 981975 (C4 (Web Text))

Max Activating Token Index: 828

Text #1

Max Range: 0.7075. Min Range: -0.7075

Max Act: 0.5983. Min Act: -0.0000

Data Index: 549974 (C4 (Web Text))

Max Activating Token Index: 529

Text #2

Max Range: 0.7075. Min Range: -0.7075

Max Act: 0.6396. Min Act: -0.0000

Data Index: 1315287 (C4 (Web Text))

Max Activating Token Index: 159

Text #3

Max Range: 0.7075. Min Range: -0.7075

Max Act: 0.6148. Min Act: -0.0000

Data Index: 1313177 (C4 (Web Text))

Max Activating Token Index: 808

Text #4

Max Range: 0.7075. Min Range: -0.7075

Max Act: 0.6020. Min Act: -0.0000

Data Index: 124680 (C4 (Web Text))

Max Activating Token Index: 285

Text #5

Max Range: 0.7075. Min Range: -0.7075

Max Act: 0.5753. Min Act: -0.0000

Data Index: 1342690 (C4 (Web Text))

Max Activating Token Index: 756

Text #6

Max Range: 0.7075. Min Range: -0.7075

Max Act: 0.5641. Min Act: -0.0000

Data Index: 2835 (C4 (Web Text))

Max Activating Token Index: 84

Text #7

Max Range: 0.7075. Min Range: -0.7075

Max Act: 0.5752. Min Act: -0.0000

Data Index: 961798 (C4 (Web Text))

Max Activating Token Index: 689

Text #8

Max Range: 0.7075. Min Range: -0.7075

Max Act: 0.5340. Min Act: -0.0000

Data Index: 1291056 (C4 (Web Text))

Max Activating Token Index: 922

Text #9

Max Range: 0.7075. Min Range: -0.7075

Max Act: 0.5538. Min Act: -0.0000

Data Index: 3688 (C4 (Web Text))

Max Activating Token Index: 678

Text #10

Max Range: 0.7075. Min Range: -0.7075

Max Act: 0.5152. Min Act: -0.0000

Data Index: 1162475 (C4 (Web Text))

Max Activating Token Index: 786

Text #11

Max Range: 0.7075. Min Range: -0.7075

Max Act: 0.5463. Min Act: -0.0000

Data Index: 699865 (C4 (Web Text))

Max Activating Token Index: 881

Text #12

Max Range: 0.7075. Min Range: -0.7075

Max Act: 0.5170. Min Act: -0.0000

Data Index: 1017636 (C4 (Web Text))

Max Activating Token Index: 83

Text #13

Max Range: 0.7075. Min Range: -0.7075

Max Act: 0.5144. Min Act: -0.0000

Data Index: 762554 (C4 (Web Text))

Max Activating Token Index: 76

Text #14

Max Range: 0.7075. Min Range: -0.7075

Max Act: 0.5101. Min Act: -0.0000

Data Index: 1151770 (C4 (Web Text))

Max Activating Token Index: 780

Text #15

Max Range: 0.7075. Min Range: -0.7075

Max Act: 0.5024. Min Act: -0.0000

Data Index: 952655 (C4 (Web Text))

Max Activating Token Index: 294

Text #16

Max Range: 0.7075. Min Range: -0.7075

Max Act: 0.4893. Min Act: -0.0000

Data Index: 866079 (C4 (Web Text))

Max Activating Token Index: 1020

Text #17

Max Range: 0.7075. Min Range: -0.7075

Max Act: 0.5019. Min Act: -0.0000

Data Index: 1120150 (C4 (Web Text))

Max Activating Token Index: 761

Text #18

Max Range: 0.7075. Min Range: -0.7075

Max Act: 0.4956. Min Act: -0.0000

Data Index: 1055741 (C4 (Web Text))

Max Activating Token Index: 980

Text #19

Max Range: 0.7075. Min Range: -0.7075

Max Act: 0.4870. Min Act: -0.0000

Data Index: 845299 (C4 (Web Text))

Max Activating Token Index: 1004