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

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

Neuron 253 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: 1.3077. Min Range: -1.3077

Max Act: 1.3077. Min Act: -0.0000

Data Index: 581888 (C4 (Web Text))

Max Activating Token Index: 154

Text #1

Max Range: 1.3077. Min Range: -1.3077

Max Act: 0.8781. Min Act: -0.0000

Data Index: 668364 (C4 (Web Text))

Max Activating Token Index: 754

Text #2

Max Range: 1.3077. Min Range: -1.3077

Max Act: 1.0473. Min Act: -0.0000

Data Index: 1155564 (C4 (Web Text))

Max Activating Token Index: 603

Text #3

Max Range: 1.3077. Min Range: -1.3077

Max Act: 0.8071. Min Act: -0.0000

Data Index: 1000624 (C4 (Web Text))

Max Activating Token Index: 250

Text #4

Max Range: 1.3077. Min Range: -1.3077

Max Act: 0.9043. Min Act: -0.0000

Data Index: 60139 (C4 (Web Text))

Max Activating Token Index: 889

Text #5

Max Range: 1.3077. Min Range: -1.3077

Max Act: 0.9190. Min Act: -0.0000

Data Index: 330637 (C4 (Web Text))

Max Activating Token Index: 507

Text #6

Max Range: 1.3077. Min Range: -1.3077

Max Act: 0.8799. Min Act: -0.0000

Data Index: 214518 (C4 (Web Text))

Max Activating Token Index: 662

Text #7

Max Range: 1.3077. Min Range: -1.3077

Max Act: 0.9509. Min Act: -0.0000

Data Index: 244444 (C4 (Web Text))

Max Activating Token Index: 218

Text #8

Max Range: 1.3077. Min Range: -1.3077

Max Act: 0.8271. Min Act: -0.0000

Data Index: 316239 (C4 (Web Text))

Max Activating Token Index: 160

Text #9

Max Range: 1.3077. Min Range: -1.3077

Max Act: 0.8441. Min Act: -0.0000

Data Index: 1141816 (C4 (Web Text))

Max Activating Token Index: 713

Text #10

Max Range: 1.3077. Min Range: -1.3077

Max Act: 0.8752. Min Act: -0.0000

Data Index: 377598 (C4 (Web Text))

Max Activating Token Index: 766

Text #11

Max Range: 1.3077. Min Range: -1.3077

Max Act: 0.8440. Min Act: -0.0000

Data Index: 728753 (C4 (Web Text))

Max Activating Token Index: 382

Text #12

Max Range: 1.3077. Min Range: -1.3077

Max Act: 0.8842. Min Act: -0.0000

Data Index: 1171598 (C4 (Web Text))

Max Activating Token Index: 795

Text #13

Max Range: 1.3077. Min Range: -1.3077

Max Act: 0.8382. Min Act: -0.0000

Data Index: 39607 (C4 (Web Text))

Max Activating Token Index: 708

Text #14

Max Range: 1.3077. Min Range: -1.3077

Max Act: 0.8657. Min Act: -0.0000

Data Index: 29910 (C4 (Web Text))

Max Activating Token Index: 871

Text #15

Max Range: 1.3077. Min Range: -1.3077

Max Act: 0.9073. Min Act: -0.0000

Data Index: 474478 (C4 (Web Text))

Max Activating Token Index: 734

Text #16

Max Range: 1.3077. Min Range: -1.3077

Max Act: 0.8620. Min Act: -0.0000

Data Index: 1285275 (C4 (Web Text))

Max Activating Token Index: 669

Text #17

Max Range: 1.3077. Min Range: -1.3077

Max Act: 0.7905. Min Act: -0.0000

Data Index: 325357 (C4 (Web Text))

Max Activating Token Index: 679

Text #18

Max Range: 1.3077. Min Range: -1.3077

Max Act: 0.7725. Min Act: -0.0000

Data Index: 1063253 (C4 (Web Text))

Max Activating Token Index: 435

Text #19

Max Range: 1.3077. Min Range: -1.3077

Max Act: 0.8458. Min Act: -0.0000

Data Index: 1104886 (C4 (Web Text))

Max Activating Token Index: 938