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

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

Neuron 1850 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9079. Min Range: -0.9079

Max Act: 0.9079. Min Act: -0.0000

Data Index: 606080 (C4 (Web Text))

Max Activating Token Index: 172

Text #1

Max Range: 0.9079. Min Range: -0.9079

Max Act: 0.7101. Min Act: -0.0000

Data Index: 1192762 (C4 (Web Text))

Max Activating Token Index: 299

Text #2

Max Range: 0.9079. Min Range: -0.9079

Max Act: 0.7589. Min Act: -0.0000

Data Index: 1292230 (C4 (Web Text))

Max Activating Token Index: 433

Text #3

Max Range: 0.9079. Min Range: -0.9079

Max Act: 0.7426. Min Act: -0.0000

Data Index: 1300141 (C4 (Web Text))

Max Activating Token Index: 718

Text #4

Max Range: 0.9079. Min Range: -0.9079

Max Act: 0.6552. Min Act: -0.0000

Data Index: 1325344 (C4 (Web Text))

Max Activating Token Index: 136

Text #5

Max Range: 0.9079. Min Range: -0.9079

Max Act: 0.6954. Min Act: -0.0000

Data Index: 1637426 (Python Code)

Max Activating Token Index: 851

Text #6

Max Range: 0.9079. Min Range: -0.9079

Max Act: 0.6454. Min Act: -0.0000

Data Index: 1054557 (C4 (Web Text))

Max Activating Token Index: 1016

Text #7

Max Range: 0.9079. Min Range: -0.9079

Max Act: 0.6366. Min Act: -0.0000

Data Index: 1603033 (Python Code)

Max Activating Token Index: 99

Text #8

Max Range: 0.9079. Min Range: -0.9079

Max Act: 0.6101. Min Act: -0.0000

Data Index: 36859 (C4 (Web Text))

Max Activating Token Index: 175

Text #9

Max Range: 0.9079. Min Range: -0.9079

Max Act: 0.6750. Min Act: -0.0000

Data Index: 1018436 (C4 (Web Text))

Max Activating Token Index: 923

Text #10

Max Range: 0.9079. Min Range: -0.9079

Max Act: 0.6089. Min Act: -0.0000

Data Index: 818079 (C4 (Web Text))

Max Activating Token Index: 352

Text #11

Max Range: 0.9079. Min Range: -0.9079

Max Act: 0.6302. Min Act: -0.0000

Data Index: 1016440 (C4 (Web Text))

Max Activating Token Index: 147

Text #12

Max Range: 0.9079. Min Range: -0.9079

Max Act: 0.5760. Min Act: -0.0000

Data Index: 1169057 (C4 (Web Text))

Max Activating Token Index: 695

Text #13

Max Range: 0.9079. Min Range: -0.9079

Max Act: 0.5743. Min Act: -0.0000

Data Index: 1067714 (C4 (Web Text))

Max Activating Token Index: 670

Text #14

Max Range: 0.9079. Min Range: -0.9079

Max Act: 0.5915. Min Act: -0.0000

Data Index: 968007 (C4 (Web Text))

Max Activating Token Index: 86

Text #15

Max Range: 0.9079. Min Range: -0.9079

Max Act: 0.6216. Min Act: -0.0000

Data Index: 982744 (C4 (Web Text))

Max Activating Token Index: 226

Text #16

Max Range: 0.9079. Min Range: -0.9079

Max Act: 0.6136. Min Act: -0.0000

Data Index: 1150788 (C4 (Web Text))

Max Activating Token Index: 5

Text #17

Max Range: 0.9079. Min Range: -0.9079

Max Act: 0.5854. Min Act: -0.0000

Data Index: 1065868 (C4 (Web Text))

Max Activating Token Index: 900

Text #18

Max Range: 0.9079. Min Range: -0.9079

Max Act: 0.6172. Min Act: -0.0000

Data Index: 753345 (C4 (Web Text))

Max Activating Token Index: 858

Text #19

Max Range: 0.9079. Min Range: -0.9079

Max Act: 0.6049. Min Act: -0.0000

Data Index: 515359 (C4 (Web Text))

Max Activating Token Index: 1019