Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5816 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.5183. Min Range: -0.5183

Max Act: 0.5183. Min Act: -0.0000

Data Index: 879089 (C4 (Web Text))

Max Activating Token Index: 59

Text #1

Max Range: 0.5183. Min Range: -0.5183

Max Act: 0.4915. Min Act: -0.0000

Data Index: 705449 (C4 (Web Text))

Max Activating Token Index: 752

Text #2

Max Range: 0.5183. Min Range: -0.5183

Max Act: 0.4743. Min Act: -0.0000

Data Index: 52111 (C4 (Web Text))

Max Activating Token Index: 596

Text #3

Max Range: 0.5183. Min Range: -0.5183

Max Act: 0.4572. Min Act: -0.0000

Data Index: 1026726 (C4 (Web Text))

Max Activating Token Index: 80

Text #4

Max Range: 0.5183. Min Range: -0.5183

Max Act: 0.4446. Min Act: -0.0000

Data Index: 464137 (C4 (Web Text))

Max Activating Token Index: 671

Text #5

Max Range: 0.5183. Min Range: -0.5183

Max Act: 0.4354. Min Act: -0.0000

Data Index: 1649854 (Python Code)

Max Activating Token Index: 550

Text #6

Max Range: 0.5183. Min Range: -0.5183

Max Act: 0.4504. Min Act: 0.0001

Data Index: 1318140 (C4 (Web Text))

Max Activating Token Index: 503

Text #7

Max Range: 0.5183. Min Range: -0.5183

Max Act: 0.4260. Min Act: -0.0000

Data Index: 1033664 (C4 (Web Text))

Max Activating Token Index: 648

Text #8

Max Range: 0.5183. Min Range: -0.5183

Max Act: 0.4182. Min Act: 0.0000

Data Index: 1449544 (Python Code)

Max Activating Token Index: 470

Text #9

Max Range: 0.5183. Min Range: -0.5183

Max Act: 0.4175. Min Act: -0.0000

Data Index: 1045849 (C4 (Web Text))

Max Activating Token Index: 52

Text #10

Max Range: 0.5183. Min Range: -0.5183

Max Act: 0.4200. Min Act: -0.0000

Data Index: 728591 (C4 (Web Text))

Max Activating Token Index: 674

Text #11

Max Range: 0.5183. Min Range: -0.5183

Max Act: 0.4083. Min Act: 0.0000

Data Index: 1543191 (Python Code)

Max Activating Token Index: 386

Text #12

Max Range: 0.5183. Min Range: -0.5183

Max Act: 0.4102. Min Act: -0.0000

Data Index: 119100 (C4 (Web Text))

Max Activating Token Index: 837

Text #13

Max Range: 0.5183. Min Range: -0.5183

Max Act: 0.3915. Min Act: -0.0000

Data Index: 1561911 (Python Code)

Max Activating Token Index: 224

Text #14

Max Range: 0.5183. Min Range: -0.5183

Max Act: 0.3917. Min Act: -0.0000

Data Index: 1471369 (Python Code)

Max Activating Token Index: 246

Text #15

Max Range: 0.5183. Min Range: -0.5183

Max Act: 0.3807. Min Act: -0.0000

Data Index: 263395 (C4 (Web Text))

Max Activating Token Index: 229

Text #16

Max Range: 0.5183. Min Range: -0.5183

Max Act: 0.3847. Min Act: -0.0000

Data Index: 1485367 (Python Code)

Max Activating Token Index: 55

Text #17

Max Range: 0.5183. Min Range: -0.5183

Max Act: 0.3811. Min Act: -0.0000

Data Index: 482657 (C4 (Web Text))

Max Activating Token Index: 176

Text #18

Max Range: 0.5183. Min Range: -0.5183

Max Act: 0.3681. Min Act: -0.0000

Data Index: 193166 (C4 (Web Text))

Max Activating Token Index: 834

Text #19

Max Range: 0.5183. Min Range: -0.5183

Max Act: 0.3854. Min Act: -0.0000

Data Index: 818817 (C4 (Web Text))

Max Activating Token Index: 143