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

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

Neuron 3499 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1752. Min Range: -2.1752

Max Act: 2.1752. Min Act: -0.0000

Data Index: 50601 (C4 (Web Text))

Max Activating Token Index: 736

Text #1

Max Range: 2.1752. Min Range: -2.1752

Max Act: 2.1404. Min Act: -0.0000

Data Index: 537605 (C4 (Web Text))

Max Activating Token Index: 163

Text #2

Max Range: 2.1752. Min Range: -2.1752

Max Act: 2.0669. Min Act: -0.0000

Data Index: 368392 (C4 (Web Text))

Max Activating Token Index: 477

Text #3

Max Range: 2.1752. Min Range: -2.1752

Max Act: 2.1459. Min Act: -0.0000

Data Index: 484377 (C4 (Web Text))

Max Activating Token Index: 488

Text #4

Max Range: 2.1752. Min Range: -2.1752

Max Act: 1.8216. Min Act: -0.0000

Data Index: 510359 (C4 (Web Text))

Max Activating Token Index: 1008

Text #5

Max Range: 2.1752. Min Range: -2.1752

Max Act: 2.0222. Min Act: -0.0000

Data Index: 1028403 (C4 (Web Text))

Max Activating Token Index: 782

Text #6

Max Range: 2.1752. Min Range: -2.1752

Max Act: 1.7783. Min Act: -0.0000

Data Index: 124767 (C4 (Web Text))

Max Activating Token Index: 989

Text #7

Max Range: 2.1752. Min Range: -2.1752

Max Act: 1.7579. Min Act: -0.0000

Data Index: 1046138 (C4 (Web Text))

Max Activating Token Index: 903

Text #8

Max Range: 2.1752. Min Range: -2.1752

Max Act: 1.8693. Min Act: -0.0000

Data Index: 1058221 (C4 (Web Text))

Max Activating Token Index: 669

Text #9

Max Range: 2.1752. Min Range: -2.1752

Max Act: 1.9585. Min Act: -0.0000

Data Index: 183479 (C4 (Web Text))

Max Activating Token Index: 799

Text #10

Max Range: 2.1752. Min Range: -2.1752

Max Act: 1.8497. Min Act: -0.0000

Data Index: 51441 (C4 (Web Text))

Max Activating Token Index: 168

Text #11

Max Range: 2.1752. Min Range: -2.1752

Max Act: 1.8208. Min Act: -0.0000

Data Index: 1125218 (C4 (Web Text))

Max Activating Token Index: 830

Text #12

Max Range: 2.1752. Min Range: -2.1752

Max Act: 1.7467. Min Act: -0.0000

Data Index: 680963 (C4 (Web Text))

Max Activating Token Index: 712

Text #13

Max Range: 2.1752. Min Range: -2.1752

Max Act: 1.8248. Min Act: -0.0000

Data Index: 478185 (C4 (Web Text))

Max Activating Token Index: 80

Text #14

Max Range: 2.1752. Min Range: -2.1752

Max Act: 1.7266. Min Act: -0.0000

Data Index: 371289 (C4 (Web Text))

Max Activating Token Index: 935

Text #15

Max Range: 2.1752. Min Range: -2.1752

Max Act: 1.7165. Min Act: -0.0000

Data Index: 1159308 (C4 (Web Text))

Max Activating Token Index: 691

Text #16

Max Range: 2.1752. Min Range: -2.1752

Max Act: 1.6867. Min Act: -0.0000

Data Index: 782131 (C4 (Web Text))

Max Activating Token Index: 986

Text #17

Max Range: 2.1752. Min Range: -2.1752

Max Act: 1.6753. Min Act: -0.0000

Data Index: 692008 (C4 (Web Text))

Max Activating Token Index: 93

Text #18

Max Range: 2.1752. Min Range: -2.1752

Max Act: 1.6717. Min Act: -0.0000

Data Index: 923745 (C4 (Web Text))

Max Activating Token Index: 903

Text #19

Max Range: 2.1752. Min Range: -2.1752

Max Act: 1.6187. Min Act: -0.0000

Data Index: 239053 (C4 (Web Text))

Max Activating Token Index: 862