Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2336 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.9425. Min Range: -0.9425

Max Act: 0.9425. Min Act: -0.0000

Data Index: 576059 (C4 (Web Text))

Max Activating Token Index: 136

Text #1

Max Range: 0.9425. Min Range: -0.9425

Max Act: 0.8050. Min Act: -0.0000

Data Index: 1033179 (C4 (Web Text))

Max Activating Token Index: 164

Text #2

Max Range: 0.9425. Min Range: -0.9425

Max Act: 0.7327. Min Act: -0.0000

Data Index: 887388 (C4 (Web Text))

Max Activating Token Index: 193

Text #3

Max Range: 0.9425. Min Range: -0.9425

Max Act: 0.6530. Min Act: -0.0000

Data Index: 1090235 (C4 (Web Text))

Max Activating Token Index: 131

Text #4

Max Range: 0.9425. Min Range: -0.9425

Max Act: 0.6769. Min Act: -0.0000

Data Index: 840896 (C4 (Web Text))

Max Activating Token Index: 161

Text #5

Max Range: 0.9425. Min Range: -0.9425

Max Act: 0.7047. Min Act: -0.0000

Data Index: 726997 (C4 (Web Text))

Max Activating Token Index: 259

Text #6

Max Range: 0.9425. Min Range: -0.9425

Max Act: 0.6781. Min Act: -0.0000

Data Index: 1529347 (Python Code)

Max Activating Token Index: 755

Text #7

Max Range: 0.9425. Min Range: -0.9425

Max Act: 0.5809. Min Act: -0.0000

Data Index: 1638132 (Python Code)

Max Activating Token Index: 769

Text #8

Max Range: 0.9425. Min Range: -0.9425

Max Act: 0.6347. Min Act: -0.0000

Data Index: 975959 (C4 (Web Text))

Max Activating Token Index: 76

Text #9

Max Range: 0.9425. Min Range: -0.9425

Max Act: 0.5991. Min Act: -0.0000

Data Index: 862895 (C4 (Web Text))

Max Activating Token Index: 178

Text #10

Max Range: 0.9425. Min Range: -0.9425

Max Act: 0.5840. Min Act: -0.0000

Data Index: 771540 (C4 (Web Text))

Max Activating Token Index: 46

Text #11

Max Range: 0.9425. Min Range: -0.9425

Max Act: 0.5698. Min Act: -0.0000

Data Index: 754981 (C4 (Web Text))

Max Activating Token Index: 77

Text #12

Max Range: 0.9425. Min Range: -0.9425

Max Act: 0.5272. Min Act: -0.0000

Data Index: 1428719 (Python Code)

Max Activating Token Index: 179

Text #13

Max Range: 0.9425. Min Range: -0.9425

Max Act: 0.5051. Min Act: -0.0000

Data Index: 1557811 (Python Code)

Max Activating Token Index: 568

Text #14

Max Range: 0.9425. Min Range: -0.9425

Max Act: 0.5180. Min Act: -0.0000

Data Index: 882313 (C4 (Web Text))

Max Activating Token Index: 135

Text #15

Max Range: 0.9425. Min Range: -0.9425

Max Act: 0.4785. Min Act: -0.0000

Data Index: 207581 (C4 (Web Text))

Max Activating Token Index: 214

Text #16

Max Range: 0.9425. Min Range: -0.9425

Max Act: 0.4593. Min Act: -0.0000

Data Index: 1438045 (Python Code)

Max Activating Token Index: 387

Text #17

Max Range: 0.9425. Min Range: -0.9425

Max Act: 0.4509. Min Act: -0.0000

Data Index: 1635721 (Python Code)

Max Activating Token Index: 330

Text #18

Max Range: 0.9425. Min Range: -0.9425

Max Act: 0.4764. Min Act: -0.0000

Data Index: 1522754 (Python Code)

Max Activating Token Index: 866

Text #19

Max Range: 0.9425. Min Range: -0.9425

Max Act: 0.4468. Min Act: -0.0000

Data Index: 1016424 (C4 (Web Text))

Max Activating Token Index: 508