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

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

Neuron 995 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3863. Min Range: -2.3863

Max Act: 2.2514. Min Act: -0.0000

Data Index: 1183088 (C4 (Web Text))

Max Activating Token Index: 982

Text #1

Max Range: 2.3863. Min Range: -2.3863

Max Act: 2.3863. Min Act: -0.0000

Data Index: 1143131 (C4 (Web Text))

Max Activating Token Index: 903

Text #2

Max Range: 2.3863. Min Range: -2.3863

Max Act: 2.0144. Min Act: -0.0000

Data Index: 820766 (C4 (Web Text))

Max Activating Token Index: 770

Text #3

Max Range: 2.3863. Min Range: -2.3863

Max Act: 2.1325. Min Act: -0.0000

Data Index: 336021 (C4 (Web Text))

Max Activating Token Index: 929

Text #4

Max Range: 2.3863. Min Range: -2.3863

Max Act: 1.8524. Min Act: -0.0000

Data Index: 1045767 (C4 (Web Text))

Max Activating Token Index: 197

Text #5

Max Range: 2.3863. Min Range: -2.3863

Max Act: 2.0425. Min Act: -0.0000

Data Index: 1288795 (C4 (Web Text))

Max Activating Token Index: 188

Text #6

Max Range: 2.3863. Min Range: -2.3863

Max Act: 2.2124. Min Act: -0.0000

Data Index: 1068356 (C4 (Web Text))

Max Activating Token Index: 183

Text #7

Max Range: 2.3863. Min Range: -2.3863

Max Act: 2.2651. Min Act: -0.0000

Data Index: 806265 (C4 (Web Text))

Max Activating Token Index: 977

Text #8

Max Range: 2.3863. Min Range: -2.3863

Max Act: 1.8745. Min Act: -0.0000

Data Index: 1326388 (C4 (Web Text))

Max Activating Token Index: 1000

Text #9

Max Range: 2.3863. Min Range: -2.3863

Max Act: 1.9193. Min Act: -0.0000

Data Index: 1055905 (C4 (Web Text))

Max Activating Token Index: 217

Text #10

Max Range: 2.3863. Min Range: -2.3863

Max Act: 1.8320. Min Act: -0.0000

Data Index: 684618 (C4 (Web Text))

Max Activating Token Index: 687

Text #11

Max Range: 2.3863. Min Range: -2.3863

Max Act: 1.7741. Min Act: -0.0000

Data Index: 197211 (C4 (Web Text))

Max Activating Token Index: 742

Text #12

Max Range: 2.3863. Min Range: -2.3863

Max Act: 2.1115. Min Act: -0.0000

Data Index: 1199055 (C4 (Web Text))

Max Activating Token Index: 864

Text #13

Max Range: 2.3863. Min Range: -2.3863

Max Act: 1.7549. Min Act: -0.0000

Data Index: 1093612 (C4 (Web Text))

Max Activating Token Index: 688

Text #14

Max Range: 2.3863. Min Range: -2.3863

Max Act: 1.6224. Min Act: -0.0000

Data Index: 83391 (C4 (Web Text))

Max Activating Token Index: 560

Text #15

Max Range: 2.3863. Min Range: -2.3863

Max Act: 1.8225. Min Act: -0.0000

Data Index: 150505 (C4 (Web Text))

Max Activating Token Index: 932

Text #16

Max Range: 2.3863. Min Range: -2.3863

Max Act: 1.7035. Min Act: -0.0000

Data Index: 802829 (C4 (Web Text))

Max Activating Token Index: 449

Text #17

Max Range: 2.3863. Min Range: -2.3863

Max Act: 1.7914. Min Act: -0.0000

Data Index: 1038362 (C4 (Web Text))

Max Activating Token Index: 624

Text #18

Max Range: 2.3863. Min Range: -2.3863

Max Act: 1.7820. Min Act: -0.0000

Data Index: 806266 (C4 (Web Text))

Max Activating Token Index: 381

Text #19

Max Range: 2.3863. Min Range: -2.3863

Max Act: 1.7613. Min Act: -0.0000

Data Index: 734723 (C4 (Web Text))

Max Activating Token Index: 679