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

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

Neuron 731 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9163. Min Range: -0.9163

Max Act: 0.9163. Min Act: -0.0000

Data Index: 856490 (C4 (Web Text))

Max Activating Token Index: 507

Text #1

Max Range: 0.9163. Min Range: -0.9163

Max Act: 0.7702. Min Act: -0.0000

Data Index: 392921 (C4 (Web Text))

Max Activating Token Index: 866

Text #2

Max Range: 0.9163. Min Range: -0.9163

Max Act: 0.7721. Min Act: -0.0001

Data Index: 1225580 (C4 (Web Text))

Max Activating Token Index: 127

Text #3

Max Range: 0.9163. Min Range: -0.9163

Max Act: 0.6654. Min Act: -0.0001

Data Index: 152060 (C4 (Web Text))

Max Activating Token Index: 777

Text #4

Max Range: 0.9163. Min Range: -0.9163

Max Act: 0.6623. Min Act: -0.0001

Data Index: 475510 (C4 (Web Text))

Max Activating Token Index: 479

Text #5

Max Range: 0.9163. Min Range: -0.9163

Max Act: 0.6590. Min Act: -0.0000

Data Index: 988627 (C4 (Web Text))

Max Activating Token Index: 971

Text #6

Max Range: 0.9163. Min Range: -0.9163

Max Act: 0.5844. Min Act: -0.0001

Data Index: 35730 (C4 (Web Text))

Max Activating Token Index: 568

Text #7

Max Range: 0.9163. Min Range: -0.9163

Max Act: 0.6388. Min Act: -0.0001

Data Index: 735674 (C4 (Web Text))

Max Activating Token Index: 186

Text #8

Max Range: 0.9163. Min Range: -0.9163

Max Act: 0.5780. Min Act: -0.0001

Data Index: 210546 (C4 (Web Text))

Max Activating Token Index: 182

Text #9

Max Range: 0.9163. Min Range: -0.9163

Max Act: 0.6054. Min Act: -0.0001

Data Index: 702529 (C4 (Web Text))

Max Activating Token Index: 735

Text #10

Max Range: 0.9163. Min Range: -0.9163

Max Act: 0.6004. Min Act: -0.0001

Data Index: 345946 (C4 (Web Text))

Max Activating Token Index: 617

Text #11

Max Range: 0.9163. Min Range: -0.9163

Max Act: 0.5652. Min Act: -0.0001

Data Index: 1351724 (C4 (Web Text))

Max Activating Token Index: 139

Text #12

Max Range: 0.9163. Min Range: -0.9163

Max Act: 0.5499. Min Act: -0.0000

Data Index: 1025815 (C4 (Web Text))

Max Activating Token Index: 816

Text #13

Max Range: 0.9163. Min Range: -0.9163

Max Act: 0.5644. Min Act: -0.0001

Data Index: 1266255 (C4 (Web Text))

Max Activating Token Index: 994

Text #14

Max Range: 0.9163. Min Range: -0.9163

Max Act: 0.6018. Min Act: -0.0001

Data Index: 35321 (C4 (Web Text))

Max Activating Token Index: 747

Text #15

Max Range: 0.9163. Min Range: -0.9163

Max Act: 0.5626. Min Act: -0.0000

Data Index: 1150731 (C4 (Web Text))

Max Activating Token Index: 122

Text #16

Max Range: 0.9163. Min Range: -0.9163

Max Act: 0.5075. Min Act: -0.0001

Data Index: 156930 (C4 (Web Text))

Max Activating Token Index: 389

Text #17

Max Range: 0.9163. Min Range: -0.9163

Max Act: 0.5552. Min Act: -0.0001

Data Index: 845527 (C4 (Web Text))

Max Activating Token Index: 478

Text #18

Max Range: 0.9163. Min Range: -0.9163

Max Act: 0.5312. Min Act: -0.0001

Data Index: 347224 (C4 (Web Text))

Max Activating Token Index: 258

Text #19

Max Range: 0.9163. Min Range: -0.9163

Max Act: 0.5290. Min Act: -0.0001

Data Index: 197347 (C4 (Web Text))

Max Activating Token Index: 405