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

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

Neuron 228 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8924. Min Range: -0.8924

Max Act: 0.8924. Min Act: -0.0001

Data Index: 107304 (C4 (Web Text))

Max Activating Token Index: 547

Text #1

Max Range: 0.8924. Min Range: -0.8924

Max Act: 0.7994. Min Act: -0.0001

Data Index: 628921 (C4 (Web Text))

Max Activating Token Index: 686

Text #2

Max Range: 0.8924. Min Range: -0.8924

Max Act: 0.8056. Min Act: -0.0001

Data Index: 809406 (C4 (Web Text))

Max Activating Token Index: 504

Text #3

Max Range: 0.8924. Min Range: -0.8924

Max Act: 0.8045. Min Act: -0.0001

Data Index: 1201528 (C4 (Web Text))

Max Activating Token Index: 490

Text #4

Max Range: 0.8924. Min Range: -0.8924

Max Act: 0.7923. Min Act: -0.0001

Data Index: 172218 (C4 (Web Text))

Max Activating Token Index: 348

Text #5

Max Range: 0.8924. Min Range: -0.8924

Max Act: 0.7219. Min Act: -0.0001

Data Index: 264030 (C4 (Web Text))

Max Activating Token Index: 244

Text #6

Max Range: 0.8924. Min Range: -0.8924

Max Act: 0.6863. Min Act: -0.0001

Data Index: 326315 (C4 (Web Text))

Max Activating Token Index: 731

Text #7

Max Range: 0.8924. Min Range: -0.8924

Max Act: 0.6793. Min Act: -0.0001

Data Index: 517064 (C4 (Web Text))

Max Activating Token Index: 193

Text #8

Max Range: 0.8924. Min Range: -0.8924

Max Act: 0.6841. Min Act: -0.0001

Data Index: 289598 (C4 (Web Text))

Max Activating Token Index: 796

Text #9

Max Range: 0.8924. Min Range: -0.8924

Max Act: 0.6286. Min Act: -0.0001

Data Index: 838119 (C4 (Web Text))

Max Activating Token Index: 160

Text #10

Max Range: 0.8924. Min Range: -0.8924

Max Act: 0.6522. Min Act: -0.0001

Data Index: 589467 (C4 (Web Text))

Max Activating Token Index: 661

Text #11

Max Range: 0.8924. Min Range: -0.8924

Max Act: 0.6695. Min Act: -0.0001

Data Index: 102753 (C4 (Web Text))

Max Activating Token Index: 845

Text #12

Max Range: 0.8924. Min Range: -0.8924

Max Act: 0.6516. Min Act: -0.0001

Data Index: 50078 (C4 (Web Text))

Max Activating Token Index: 977

Text #13

Max Range: 0.8924. Min Range: -0.8924

Max Act: 0.6965. Min Act: -0.0001

Data Index: 610318 (C4 (Web Text))

Max Activating Token Index: 273

Text #14

Max Range: 0.8924. Min Range: -0.8924

Max Act: 0.6468. Min Act: -0.0001

Data Index: 1184656 (C4 (Web Text))

Max Activating Token Index: 556

Text #15

Max Range: 0.8924. Min Range: -0.8924

Max Act: 0.6524. Min Act: -0.0001

Data Index: 191324 (C4 (Web Text))

Max Activating Token Index: 149

Text #16

Max Range: 0.8924. Min Range: -0.8924

Max Act: 0.6223. Min Act: -0.0001

Data Index: 213126 (C4 (Web Text))

Max Activating Token Index: 1005

Text #17

Max Range: 0.8924. Min Range: -0.8924

Max Act: 0.6436. Min Act: -0.0001

Data Index: 175737 (C4 (Web Text))

Max Activating Token Index: 58

Text #18

Max Range: 0.8924. Min Range: -0.8924

Max Act: 0.6421. Min Act: -0.0001

Data Index: 1195026 (C4 (Web Text))

Max Activating Token Index: 63

Text #19

Max Range: 0.8924. Min Range: -0.8924

Max Act: 0.5980. Min Act: -0.0001

Data Index: 1297582 (C4 (Web Text))

Max Activating Token Index: 637