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

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

Neuron 1304 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1069. Min Range: -1.1069

Max Act: 1.1069. Min Act: -0.0004

Data Index: 515603 (C4 (Web Text))

Max Activating Token Index: 614

Text #1

Max Range: 1.1069. Min Range: -1.1069

Max Act: 0.9614. Min Act: -0.0003

Data Index: 109017 (C4 (Web Text))

Max Activating Token Index: 410

Text #2

Max Range: 1.1069. Min Range: -1.1069

Max Act: 0.8764. Min Act: -0.0003

Data Index: 57011 (C4 (Web Text))

Max Activating Token Index: 506

Text #3

Max Range: 1.1069. Min Range: -1.1069

Max Act: 0.9112. Min Act: -0.0003

Data Index: 617614 (C4 (Web Text))

Max Activating Token Index: 57

Text #4

Max Range: 1.1069. Min Range: -1.1069

Max Act: 0.8655. Min Act: -0.0003

Data Index: 1248578 (C4 (Web Text))

Max Activating Token Index: 356

Text #5

Max Range: 1.1069. Min Range: -1.1069

Max Act: 0.8957. Min Act: -0.0003

Data Index: 797608 (C4 (Web Text))

Max Activating Token Index: 439

Text #6

Max Range: 1.1069. Min Range: -1.1069

Max Act: 0.8226. Min Act: -0.0003

Data Index: 845528 (C4 (Web Text))

Max Activating Token Index: 689

Text #7

Max Range: 1.1069. Min Range: -1.1069

Max Act: 0.7320. Min Act: -0.0003

Data Index: 542466 (C4 (Web Text))

Max Activating Token Index: 936

Text #8

Max Range: 1.1069. Min Range: -1.1069

Max Act: 0.7749. Min Act: -0.0003

Data Index: 1072864 (C4 (Web Text))

Max Activating Token Index: 990

Text #9

Max Range: 1.1069. Min Range: -1.1069

Max Act: 0.8203. Min Act: -0.0003

Data Index: 1099221 (C4 (Web Text))

Max Activating Token Index: 695

Text #10

Max Range: 1.1069. Min Range: -1.1069

Max Act: 0.8134. Min Act: -0.0003

Data Index: 228027 (C4 (Web Text))

Max Activating Token Index: 644

Text #11

Max Range: 1.1069. Min Range: -1.1069

Max Act: 0.9417. Min Act: -0.0003

Data Index: 826760 (C4 (Web Text))

Max Activating Token Index: 274

Text #12

Max Range: 1.1069. Min Range: -1.1069

Max Act: 0.6781. Min Act: -0.0003

Data Index: 93815 (C4 (Web Text))

Max Activating Token Index: 685

Text #13

Max Range: 1.1069. Min Range: -1.1069

Max Act: 0.5878. Min Act: -0.0003

Data Index: 1220301 (C4 (Web Text))

Max Activating Token Index: 670

Text #14

Max Range: 1.1069. Min Range: -1.1069

Max Act: 0.8172. Min Act: -0.0003

Data Index: 590449 (C4 (Web Text))

Max Activating Token Index: 883

Text #15

Max Range: 1.1069. Min Range: -1.1069

Max Act: 0.7616. Min Act: -0.0003

Data Index: 1167252 (C4 (Web Text))

Max Activating Token Index: 149

Text #16

Max Range: 1.1069. Min Range: -1.1069

Max Act: 0.7156. Min Act: -0.0003

Data Index: 1328050 (C4 (Web Text))

Max Activating Token Index: 544

Text #17

Max Range: 1.1069. Min Range: -1.1069

Max Act: 0.8515. Min Act: -0.0003

Data Index: 607083 (C4 (Web Text))

Max Activating Token Index: 702

Text #18

Max Range: 1.1069. Min Range: -1.1069

Max Act: 0.7995. Min Act: -0.0003

Data Index: 1203111 (C4 (Web Text))

Max Activating Token Index: 439

Text #19

Max Range: 1.1069. Min Range: -1.1069

Max Act: 0.8199. Min Act: -0.0003

Data Index: 210706 (C4 (Web Text))

Max Activating Token Index: 596