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

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

Neuron 1241 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8900. Min Range: -1.8900

Max Act: 1.8850. Min Act: -0.0001

Data Index: 1323685 (C4 (Web Text))

Max Activating Token Index: 656

Text #1

Max Range: 1.8900. Min Range: -1.8900

Max Act: 1.8180. Min Act: -0.0001

Data Index: 100299 (C4 (Web Text))

Max Activating Token Index: 623

Text #2

Max Range: 1.8900. Min Range: -1.8900

Max Act: 1.8196. Min Act: -0.0001

Data Index: 1144731 (C4 (Web Text))

Max Activating Token Index: 131

Text #3

Max Range: 1.8900. Min Range: -1.8900

Max Act: 1.7390. Min Act: -0.0001

Data Index: 875792 (C4 (Web Text))

Max Activating Token Index: 24

Text #4

Max Range: 1.8900. Min Range: -1.8900

Max Act: 1.8900. Min Act: -0.0001

Data Index: 114541 (C4 (Web Text))

Max Activating Token Index: 227

Text #5

Max Range: 1.8900. Min Range: -1.8900

Max Act: 1.8272. Min Act: -0.0001

Data Index: 385388 (C4 (Web Text))

Max Activating Token Index: 193

Text #6

Max Range: 1.8900. Min Range: -1.8900

Max Act: 1.6381. Min Act: -0.0001

Data Index: 1310593 (C4 (Web Text))

Max Activating Token Index: 232

Text #7

Max Range: 1.8900. Min Range: -1.8900

Max Act: 1.7104. Min Act: -0.0001

Data Index: 1304737 (C4 (Web Text))

Max Activating Token Index: 180

Text #8

Max Range: 1.8900. Min Range: -1.8900

Max Act: 1.7137. Min Act: -0.0001

Data Index: 1271064 (C4 (Web Text))

Max Activating Token Index: 338

Text #9

Max Range: 1.8900. Min Range: -1.8900

Max Act: 1.6276. Min Act: -0.0001

Data Index: 466893 (C4 (Web Text))

Max Activating Token Index: 547

Text #10

Max Range: 1.8900. Min Range: -1.8900

Max Act: 1.6605. Min Act: -0.0001

Data Index: 1143351 (C4 (Web Text))

Max Activating Token Index: 496

Text #11

Max Range: 1.8900. Min Range: -1.8900

Max Act: 1.7362. Min Act: -0.0001

Data Index: 372677 (C4 (Web Text))

Max Activating Token Index: 919

Text #12

Max Range: 1.8900. Min Range: -1.8900

Max Act: 1.5582. Min Act: -0.0001

Data Index: 14484 (C4 (Web Text))

Max Activating Token Index: 740

Text #13

Max Range: 1.8900. Min Range: -1.8900

Max Act: 1.6841. Min Act: -0.0001

Data Index: 48267 (C4 (Web Text))

Max Activating Token Index: 850

Text #14

Max Range: 1.8900. Min Range: -1.8900

Max Act: 1.5513. Min Act: -0.0001

Data Index: 323643 (C4 (Web Text))

Max Activating Token Index: 842

Text #15

Max Range: 1.8900. Min Range: -1.8900

Max Act: 1.5981. Min Act: -0.0001

Data Index: 1315843 (C4 (Web Text))

Max Activating Token Index: 880

Text #16

Max Range: 1.8900. Min Range: -1.8900

Max Act: 1.6400. Min Act: -0.0001

Data Index: 824322 (C4 (Web Text))

Max Activating Token Index: 43

Text #17

Max Range: 1.8900. Min Range: -1.8900

Max Act: 1.5439. Min Act: -0.0001

Data Index: 994729 (C4 (Web Text))

Max Activating Token Index: 235

Text #18

Max Range: 1.8900. Min Range: -1.8900

Max Act: 1.5785. Min Act: -0.0001

Data Index: 913793 (C4 (Web Text))

Max Activating Token Index: 469

Text #19

Max Range: 1.8900. Min Range: -1.8900

Max Act: 1.6309. Min Act: -0.0001

Data Index: 154180 (C4 (Web Text))

Max Activating Token Index: 103