Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 896 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.8081. Min Range: -0.8081

Max Act: 0.8081. Min Act: -0.0003

Data Index: 247574 (C4 (Web Text))

Max Activating Token Index: 215

Text #1

Max Range: 0.8081. Min Range: -0.8081

Max Act: 0.7242. Min Act: -0.0003

Data Index: 727172 (C4 (Web Text))

Max Activating Token Index: 327

Text #2

Max Range: 0.8081. Min Range: -0.8081

Max Act: 0.6602. Min Act: -0.0003

Data Index: 886284 (C4 (Web Text))

Max Activating Token Index: 55

Text #3

Max Range: 0.8081. Min Range: -0.8081

Max Act: 0.6540. Min Act: -0.0003

Data Index: 273353 (C4 (Web Text))

Max Activating Token Index: 701

Text #4

Max Range: 0.8081. Min Range: -0.8081

Max Act: 0.6919. Min Act: -0.0003

Data Index: 661859 (C4 (Web Text))

Max Activating Token Index: 552

Text #5

Max Range: 0.8081. Min Range: -0.8081

Max Act: 0.6191. Min Act: -0.0003

Data Index: 730999 (C4 (Web Text))

Max Activating Token Index: 623

Text #6

Max Range: 0.8081. Min Range: -0.8081

Max Act: 0.6146. Min Act: -0.0003

Data Index: 1260661 (C4 (Web Text))

Max Activating Token Index: 394

Text #7

Max Range: 0.8081. Min Range: -0.8081

Max Act: 0.6440. Min Act: -0.0003

Data Index: 1278995 (C4 (Web Text))

Max Activating Token Index: 69

Text #8

Max Range: 0.8081. Min Range: -0.8081

Max Act: 0.5566. Min Act: -0.0003

Data Index: 349342 (C4 (Web Text))

Max Activating Token Index: 515

Text #9

Max Range: 0.8081. Min Range: -0.8081

Max Act: 0.5915. Min Act: -0.0003

Data Index: 663131 (C4 (Web Text))

Max Activating Token Index: 804

Text #10

Max Range: 0.8081. Min Range: -0.8081

Max Act: 0.6001. Min Act: -0.0003

Data Index: 443391 (C4 (Web Text))

Max Activating Token Index: 238

Text #11

Max Range: 0.8081. Min Range: -0.8081

Max Act: 0.5602. Min Act: -0.0003

Data Index: 830312 (C4 (Web Text))

Max Activating Token Index: 470

Text #12

Max Range: 0.8081. Min Range: -0.8081

Max Act: 0.5656. Min Act: -0.0003

Data Index: 357354 (C4 (Web Text))

Max Activating Token Index: 971

Text #13

Max Range: 0.8081. Min Range: -0.8081

Max Act: 0.6002. Min Act: -0.0003

Data Index: 1046508 (C4 (Web Text))

Max Activating Token Index: 564

Text #14

Max Range: 0.8081. Min Range: -0.8081

Max Act: 0.5809. Min Act: -0.0003

Data Index: 500620 (C4 (Web Text))

Max Activating Token Index: 656

Text #15

Max Range: 0.8081. Min Range: -0.8081

Max Act: 0.5414. Min Act: -0.0003

Data Index: 726075 (C4 (Web Text))

Max Activating Token Index: 32

Text #16

Max Range: 0.8081. Min Range: -0.8081

Max Act: 0.4865. Min Act: -0.0003

Data Index: 224186 (C4 (Web Text))

Max Activating Token Index: 239

Text #17

Max Range: 0.8081. Min Range: -0.8081

Max Act: 0.5713. Min Act: -0.0003

Data Index: 227027 (C4 (Web Text))

Max Activating Token Index: 14

Text #18

Max Range: 0.8081. Min Range: -0.8081

Max Act: 0.5800. Min Act: -0.0003

Data Index: 2063 (C4 (Web Text))

Max Activating Token Index: 308

Text #19

Max Range: 0.8081. Min Range: -0.8081

Max Act: 0.5381. Min Act: -0.0003

Data Index: 1238973 (C4 (Web Text))

Max Activating Token Index: 252