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

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

Neuron 3126 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8278. Min Range: -0.8278

Max Act: 0.8278. Min Act: -0.0001

Data Index: 1212863 (C4 (Web Text))

Max Activating Token Index: 156

Text #1

Max Range: 0.8278. Min Range: -0.8278

Max Act: 0.6929. Min Act: -0.0001

Data Index: 1225310 (C4 (Web Text))

Max Activating Token Index: 915

Text #2

Max Range: 0.8278. Min Range: -0.8278

Max Act: 0.6864. Min Act: -0.0001

Data Index: 1121702 (C4 (Web Text))

Max Activating Token Index: 384

Text #3

Max Range: 0.8278. Min Range: -0.8278

Max Act: 0.6878. Min Act: -0.0001

Data Index: 783998 (C4 (Web Text))

Max Activating Token Index: 942

Text #4

Max Range: 0.8278. Min Range: -0.8278

Max Act: 0.6866. Min Act: -0.0001

Data Index: 1194189 (C4 (Web Text))

Max Activating Token Index: 108

Text #5

Max Range: 0.8278. Min Range: -0.8278

Max Act: 0.6477. Min Act: -0.0001

Data Index: 717788 (C4 (Web Text))

Max Activating Token Index: 280

Text #6

Max Range: 0.8278. Min Range: -0.8278

Max Act: 0.6155. Min Act: -0.0001

Data Index: 353878 (C4 (Web Text))

Max Activating Token Index: 472

Text #7

Max Range: 0.8278. Min Range: -0.8278

Max Act: 0.6149. Min Act: -0.0001

Data Index: 569412 (C4 (Web Text))

Max Activating Token Index: 197

Text #8

Max Range: 0.8278. Min Range: -0.8278

Max Act: 0.6406. Min Act: -0.0001

Data Index: 286269 (C4 (Web Text))

Max Activating Token Index: 400

Text #9

Max Range: 0.8278. Min Range: -0.8278

Max Act: 0.6276. Min Act: -0.0001

Data Index: 954832 (C4 (Web Text))

Max Activating Token Index: 43

Text #10

Max Range: 0.8278. Min Range: -0.8278

Max Act: 0.6337. Min Act: -0.0001

Data Index: 688153 (C4 (Web Text))

Max Activating Token Index: 459

Text #11

Max Range: 0.8278. Min Range: -0.8278

Max Act: 0.6378. Min Act: -0.0001

Data Index: 44557 (C4 (Web Text))

Max Activating Token Index: 329

Text #12

Max Range: 0.8278. Min Range: -0.8278

Max Act: 0.6634. Min Act: -0.0001

Data Index: 524655 (C4 (Web Text))

Max Activating Token Index: 289

Text #13

Max Range: 0.8278. Min Range: -0.8278

Max Act: 0.6278. Min Act: -0.0001

Data Index: 129176 (C4 (Web Text))

Max Activating Token Index: 682

Text #14

Max Range: 0.8278. Min Range: -0.8278

Max Act: 0.6804. Min Act: -0.0001

Data Index: 844978 (C4 (Web Text))

Max Activating Token Index: 610

Text #15

Max Range: 0.8278. Min Range: -0.8278

Max Act: 0.5964. Min Act: -0.0001

Data Index: 298365 (C4 (Web Text))

Max Activating Token Index: 924

Text #16

Max Range: 0.8278. Min Range: -0.8278

Max Act: 0.6151. Min Act: -0.0001

Data Index: 457697 (C4 (Web Text))

Max Activating Token Index: 168

Text #17

Max Range: 0.8278. Min Range: -0.8278

Max Act: 0.6144. Min Act: -0.0001

Data Index: 892496 (C4 (Web Text))

Max Activating Token Index: 475

Text #18

Max Range: 0.8278. Min Range: -0.8278

Max Act: 0.5733. Min Act: -0.0001

Data Index: 473742 (C4 (Web Text))

Max Activating Token Index: 904

Text #19

Max Range: 0.8278. Min Range: -0.8278

Max Act: 0.5939. Min Act: -0.0001

Data Index: 148591 (C4 (Web Text))

Max Activating Token Index: 68