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

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

Neuron 591 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: 6.2819. Min Range: -6.2819

Max Act: 6.2819. Min Act: -0.0000

Data Index: 560642 (C4 (Web Text))

Max Activating Token Index: 22

Text #1

Max Range: 6.2819. Min Range: -6.2819

Max Act: 5.5959. Min Act: -0.0000

Data Index: 1331591 (C4 (Web Text))

Max Activating Token Index: 73

Text #2

Max Range: 6.2819. Min Range: -6.2819

Max Act: 5.3240. Min Act: -0.0000

Data Index: 1289744 (C4 (Web Text))

Max Activating Token Index: 156

Text #3

Max Range: 6.2819. Min Range: -6.2819

Max Act: 5.0413. Min Act: -0.0000

Data Index: 1192812 (C4 (Web Text))

Max Activating Token Index: 142

Text #4

Max Range: 6.2819. Min Range: -6.2819

Max Act: 5.1794. Min Act: -0.0000

Data Index: 334533 (C4 (Web Text))

Max Activating Token Index: 103

Text #5

Max Range: 6.2819. Min Range: -6.2819

Max Act: 4.8027. Min Act: -0.0000

Data Index: 133315 (C4 (Web Text))

Max Activating Token Index: 72

Text #6

Max Range: 6.2819. Min Range: -6.2819

Max Act: 5.3195. Min Act: -0.0000

Data Index: 936666 (C4 (Web Text))

Max Activating Token Index: 224

Text #7

Max Range: 6.2819. Min Range: -6.2819

Max Act: 4.9115. Min Act: -0.0000

Data Index: 1016910 (C4 (Web Text))

Max Activating Token Index: 97

Text #8

Max Range: 6.2819. Min Range: -6.2819

Max Act: 4.5336. Min Act: -0.0000

Data Index: 198047 (C4 (Web Text))

Max Activating Token Index: 40

Text #9

Max Range: 6.2819. Min Range: -6.2819

Max Act: 4.3109. Min Act: -0.0000

Data Index: 486294 (C4 (Web Text))

Max Activating Token Index: 9

Text #10

Max Range: 6.2819. Min Range: -6.2819

Max Act: 4.2949. Min Act: -0.0000

Data Index: 1237449 (C4 (Web Text))

Max Activating Token Index: 723

Text #11

Max Range: 6.2819. Min Range: -6.2819

Max Act: 4.4646. Min Act: -0.0000

Data Index: 1235380 (C4 (Web Text))

Max Activating Token Index: 186

Text #12

Max Range: 6.2819. Min Range: -6.2819

Max Act: 4.4370. Min Act: -0.0000

Data Index: 1281585 (C4 (Web Text))

Max Activating Token Index: 134

Text #13

Max Range: 6.2819. Min Range: -6.2819

Max Act: 4.2440. Min Act: -0.0000

Data Index: 1324692 (C4 (Web Text))

Max Activating Token Index: 65

Text #14

Max Range: 6.2819. Min Range: -6.2819

Max Act: 4.5637. Min Act: -0.0000

Data Index: 956795 (C4 (Web Text))

Max Activating Token Index: 318

Text #15

Max Range: 6.2819. Min Range: -6.2819

Max Act: 4.3829. Min Act: -0.0000

Data Index: 652585 (C4 (Web Text))

Max Activating Token Index: 43

Text #16

Max Range: 6.2819. Min Range: -6.2819

Max Act: 4.7239. Min Act: -0.0000

Data Index: 769208 (C4 (Web Text))

Max Activating Token Index: 122

Text #17

Max Range: 6.2819. Min Range: -6.2819

Max Act: 4.1207. Min Act: -0.0000

Data Index: 393055 (C4 (Web Text))

Max Activating Token Index: 21

Text #18

Max Range: 6.2819. Min Range: -6.2819

Max Act: 4.2497. Min Act: -0.0000

Data Index: 1236587 (C4 (Web Text))

Max Activating Token Index: 39

Text #19

Max Range: 6.2819. Min Range: -6.2819

Max Act: 4.1895. Min Act: -0.0000

Data Index: 276157 (C4 (Web Text))

Max Activating Token Index: 17