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

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

Neuron 4307 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8400. Min Range: -0.8400

Max Act: 0.8400. Min Act: -0.0002

Data Index: 1056033 (C4 (Web Text))

Max Activating Token Index: 515

Text #1

Max Range: 0.8400. Min Range: -0.8400

Max Act: 0.7380. Min Act: -0.0002

Data Index: 1290636 (C4 (Web Text))

Max Activating Token Index: 860

Text #2

Max Range: 0.8400. Min Range: -0.8400

Max Act: 0.7343. Min Act: -0.0002

Data Index: 988220 (C4 (Web Text))

Max Activating Token Index: 56

Text #3

Max Range: 0.8400. Min Range: -0.8400

Max Act: 0.6265. Min Act: -0.0002

Data Index: 1252103 (C4 (Web Text))

Max Activating Token Index: 581

Text #4

Max Range: 0.8400. Min Range: -0.8400

Max Act: 0.6770. Min Act: -0.0002

Data Index: 489809 (C4 (Web Text))

Max Activating Token Index: 581

Text #5

Max Range: 0.8400. Min Range: -0.8400

Max Act: 0.6592. Min Act: -0.0002

Data Index: 313195 (C4 (Web Text))

Max Activating Token Index: 135

Text #6

Max Range: 0.8400. Min Range: -0.8400

Max Act: 0.6122. Min Act: -0.0002

Data Index: 745808 (C4 (Web Text))

Max Activating Token Index: 637

Text #7

Max Range: 0.8400. Min Range: -0.8400

Max Act: 0.6267. Min Act: -0.0002

Data Index: 269229 (C4 (Web Text))

Max Activating Token Index: 911

Text #8

Max Range: 0.8400. Min Range: -0.8400

Max Act: 0.5779. Min Act: -0.0002

Data Index: 43562 (C4 (Web Text))

Max Activating Token Index: 165

Text #9

Max Range: 0.8400. Min Range: -0.8400

Max Act: 0.5845. Min Act: -0.0002

Data Index: 164445 (C4 (Web Text))

Max Activating Token Index: 703

Text #10

Max Range: 0.8400. Min Range: -0.8400

Max Act: 0.6899. Min Act: -0.0002

Data Index: 900967 (C4 (Web Text))

Max Activating Token Index: 147

Text #11

Max Range: 0.8400. Min Range: -0.8400

Max Act: 0.6370. Min Act: -0.0002

Data Index: 324319 (C4 (Web Text))

Max Activating Token Index: 833

Text #12

Max Range: 0.8400. Min Range: -0.8400

Max Act: 0.6171. Min Act: -0.0002

Data Index: 1163387 (C4 (Web Text))

Max Activating Token Index: 1004

Text #13

Max Range: 0.8400. Min Range: -0.8400

Max Act: 0.6155. Min Act: -0.0002

Data Index: 1089729 (C4 (Web Text))

Max Activating Token Index: 984

Text #14

Max Range: 0.8400. Min Range: -0.8400

Max Act: 0.5977. Min Act: -0.0002

Data Index: 900469 (C4 (Web Text))

Max Activating Token Index: 345

Text #15

Max Range: 0.8400. Min Range: -0.8400

Max Act: 0.5398. Min Act: -0.0002

Data Index: 1296608 (C4 (Web Text))

Max Activating Token Index: 177

Text #16

Max Range: 0.8400. Min Range: -0.8400

Max Act: 0.5517. Min Act: -0.0002

Data Index: 1031909 (C4 (Web Text))

Max Activating Token Index: 496

Text #17

Max Range: 0.8400. Min Range: -0.8400

Max Act: 0.6149. Min Act: -0.0002

Data Index: 354296 (C4 (Web Text))

Max Activating Token Index: 125

Text #18

Max Range: 0.8400. Min Range: -0.8400

Max Act: 0.5734. Min Act: -0.0002

Data Index: 164139 (C4 (Web Text))

Max Activating Token Index: 556

Text #19

Max Range: 0.8400. Min Range: -0.8400

Max Act: 0.5566. Min Act: -0.0002

Data Index: 869999 (C4 (Web Text))

Max Activating Token Index: 824