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

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

Neuron 5067 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: 0.8918. Min Range: -0.8918

Max Act: 0.8918. Min Act: 0.0001

Data Index: 80923 (C4 (Web Text))

Max Activating Token Index: 554

Text #1

Max Range: 0.8918. Min Range: -0.8918

Max Act: 0.8206. Min Act: -0.0000

Data Index: 1181141 (C4 (Web Text))

Max Activating Token Index: 801

Text #2

Max Range: 0.8918. Min Range: -0.8918

Max Act: 0.8268. Min Act: 0.0000

Data Index: 86811 (C4 (Web Text))

Max Activating Token Index: 1000

Text #3

Max Range: 0.8918. Min Range: -0.8918

Max Act: 0.7578. Min Act: 0.0001

Data Index: 921924 (C4 (Web Text))

Max Activating Token Index: 471

Text #4

Max Range: 0.8918. Min Range: -0.8918

Max Act: 0.7251. Min Act: -0.0000

Data Index: 829536 (C4 (Web Text))

Max Activating Token Index: 306

Text #5

Max Range: 0.8918. Min Range: -0.8918

Max Act: 0.7238. Min Act: -0.0000

Data Index: 744105 (C4 (Web Text))

Max Activating Token Index: 308

Text #6

Max Range: 0.8918. Min Range: -0.8918

Max Act: 0.6428. Min Act: 0.0000

Data Index: 956051 (C4 (Web Text))

Max Activating Token Index: 554

Text #7

Max Range: 0.8918. Min Range: -0.8918

Max Act: 0.6451. Min Act: 0.0000

Data Index: 221043 (C4 (Web Text))

Max Activating Token Index: 185

Text #8

Max Range: 0.8918. Min Range: -0.8918

Max Act: 0.6320. Min Act: -0.0000

Data Index: 1038046 (C4 (Web Text))

Max Activating Token Index: 963

Text #9

Max Range: 0.8918. Min Range: -0.8918

Max Act: 0.6813. Min Act: -0.0000

Data Index: 1278031 (C4 (Web Text))

Max Activating Token Index: 527

Text #10

Max Range: 0.8918. Min Range: -0.8918

Max Act: 0.6529. Min Act: 0.0001

Data Index: 774454 (C4 (Web Text))

Max Activating Token Index: 618

Text #11

Max Range: 0.8918. Min Range: -0.8918

Max Act: 0.6442. Min Act: -0.0000

Data Index: 164500 (C4 (Web Text))

Max Activating Token Index: 344

Text #12

Max Range: 0.8918. Min Range: -0.8918

Max Act: 0.6333. Min Act: -0.0000

Data Index: 585021 (C4 (Web Text))

Max Activating Token Index: 59

Text #13

Max Range: 0.8918. Min Range: -0.8918

Max Act: 0.6349. Min Act: 0.0001

Data Index: 148371 (C4 (Web Text))

Max Activating Token Index: 600

Text #14

Max Range: 0.8918. Min Range: -0.8918

Max Act: 0.6554. Min Act: -0.0000

Data Index: 814171 (C4 (Web Text))

Max Activating Token Index: 165

Text #15

Max Range: 0.8918. Min Range: -0.8918

Max Act: 0.6156. Min Act: -0.0000

Data Index: 1135402 (C4 (Web Text))

Max Activating Token Index: 131

Text #16

Max Range: 0.8918. Min Range: -0.8918

Max Act: 0.6125. Min Act: -0.0000

Data Index: 947951 (C4 (Web Text))

Max Activating Token Index: 218

Text #17

Max Range: 0.8918. Min Range: -0.8918

Max Act: 0.6122. Min Act: -0.0000

Data Index: 627614 (C4 (Web Text))

Max Activating Token Index: 204

Text #18

Max Range: 0.8918. Min Range: -0.8918

Max Act: 0.6075. Min Act: -0.0000

Data Index: 289017 (C4 (Web Text))

Max Activating Token Index: 717

Text #19

Max Range: 0.8918. Min Range: -0.8918

Max Act: 0.6071. Min Act: -0.0000

Data Index: 219965 (C4 (Web Text))

Max Activating Token Index: 808