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

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

Neuron 3266 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3627. Min Range: -0.3627

Max Act: 0.3627. Min Act: 0.0000

Data Index: 156856 (C4 (Web Text))

Max Activating Token Index: 1013

Text #1

Max Range: 0.3627. Min Range: -0.3627

Max Act: 0.2722. Min Act: -0.0000

Data Index: 764812 (C4 (Web Text))

Max Activating Token Index: 215

Text #2

Max Range: 0.3627. Min Range: -0.3627

Max Act: 0.2993. Min Act: -0.0000

Data Index: 698722 (C4 (Web Text))

Max Activating Token Index: 753

Text #3

Max Range: 0.3627. Min Range: -0.3627

Max Act: 0.2825. Min Act: -0.0000

Data Index: 789112 (C4 (Web Text))

Max Activating Token Index: 751

Text #4

Max Range: 0.3627. Min Range: -0.3627

Max Act: 0.2642. Min Act: -0.0000

Data Index: 782604 (C4 (Web Text))

Max Activating Token Index: 78

Text #5

Max Range: 0.3627. Min Range: -0.3627

Max Act: 0.2460. Min Act: -0.0000

Data Index: 727601 (C4 (Web Text))

Max Activating Token Index: 947

Text #6

Max Range: 0.3627. Min Range: -0.3627

Max Act: 0.2413. Min Act: -0.0000

Data Index: 1114011 (C4 (Web Text))

Max Activating Token Index: 687

Text #7

Max Range: 0.3627. Min Range: -0.3627

Max Act: 0.2356. Min Act: -0.0000

Data Index: 1010836 (C4 (Web Text))

Max Activating Token Index: 259

Text #8

Max Range: 0.3627. Min Range: -0.3627

Max Act: 0.2255. Min Act: -0.0000

Data Index: 755061 (C4 (Web Text))

Max Activating Token Index: 641

Text #9

Max Range: 0.3627. Min Range: -0.3627

Max Act: 0.2263. Min Act: -0.0000

Data Index: 301025 (C4 (Web Text))

Max Activating Token Index: 171

Text #10

Max Range: 0.3627. Min Range: -0.3627

Max Act: 0.2362. Min Act: -0.0000

Data Index: 397229 (C4 (Web Text))

Max Activating Token Index: 485

Text #11

Max Range: 0.3627. Min Range: -0.3627

Max Act: 0.2261. Min Act: -0.0000

Data Index: 587334 (C4 (Web Text))

Max Activating Token Index: 282

Text #12

Max Range: 0.3627. Min Range: -0.3627

Max Act: 0.2063. Min Act: -0.0000

Data Index: 826011 (C4 (Web Text))

Max Activating Token Index: 209

Text #13

Max Range: 0.3627. Min Range: -0.3627

Max Act: 0.2088. Min Act: 0.0000

Data Index: 1036644 (C4 (Web Text))

Max Activating Token Index: 101

Text #14

Max Range: 0.3627. Min Range: -0.3627

Max Act: 0.2147. Min Act: -0.0000

Data Index: 40506 (C4 (Web Text))

Max Activating Token Index: 918

Text #15

Max Range: 0.3627. Min Range: -0.3627

Max Act: 0.2046. Min Act: -0.0000

Data Index: 167492 (C4 (Web Text))

Max Activating Token Index: 736

Text #16

Max Range: 0.3627. Min Range: -0.3627

Max Act: 0.2109. Min Act: -0.0000

Data Index: 806228 (C4 (Web Text))

Max Activating Token Index: 840

Text #17

Max Range: 0.3627. Min Range: -0.3627

Max Act: 0.2080. Min Act: -0.0000

Data Index: 1206483 (C4 (Web Text))

Max Activating Token Index: 256

Text #18

Max Range: 0.3627. Min Range: -0.3627

Max Act: 0.2071. Min Act: -0.0000

Data Index: 1265361 (C4 (Web Text))

Max Activating Token Index: 86

Text #19

Max Range: 0.3627. Min Range: -0.3627

Max Act: 0.1984. Min Act: -0.0000

Data Index: 456082 (C4 (Web Text))

Max Activating Token Index: 885