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

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

Neuron 4501 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4856. Min Range: -1.4856

Max Act: 1.4856. Min Act: -0.0000

Data Index: 194081 (C4 (Web Text))

Max Activating Token Index: 35

Text #1

Max Range: 1.4856. Min Range: -1.4856

Max Act: 1.2336. Min Act: -0.0000

Data Index: 991229 (C4 (Web Text))

Max Activating Token Index: 218

Text #2

Max Range: 1.4856. Min Range: -1.4856

Max Act: 1.0667. Min Act: -0.0000

Data Index: 24011 (C4 (Web Text))

Max Activating Token Index: 141

Text #3

Max Range: 1.4856. Min Range: -1.4856

Max Act: 1.0708. Min Act: -0.0000

Data Index: 162321 (C4 (Web Text))

Max Activating Token Index: 201

Text #4

Max Range: 1.4856. Min Range: -1.4856

Max Act: 0.9610. Min Act: -0.0000

Data Index: 194365 (C4 (Web Text))

Max Activating Token Index: 861

Text #5

Max Range: 1.4856. Min Range: -1.4856

Max Act: 0.9646. Min Act: -0.0000

Data Index: 616292 (C4 (Web Text))

Max Activating Token Index: 984

Text #6

Max Range: 1.4856. Min Range: -1.4856

Max Act: 0.9432. Min Act: -0.0000

Data Index: 204804 (C4 (Web Text))

Max Activating Token Index: 13

Text #7

Max Range: 1.4856. Min Range: -1.4856

Max Act: 0.9107. Min Act: -0.0000

Data Index: 346287 (C4 (Web Text))

Max Activating Token Index: 210

Text #8

Max Range: 1.4856. Min Range: -1.4856

Max Act: 0.9517. Min Act: -0.0000

Data Index: 252011 (C4 (Web Text))

Max Activating Token Index: 704

Text #9

Max Range: 1.4856. Min Range: -1.4856

Max Act: 0.8558. Min Act: -0.0000

Data Index: 528963 (C4 (Web Text))

Max Activating Token Index: 251

Text #10

Max Range: 1.4856. Min Range: -1.4856

Max Act: 0.8981. Min Act: -0.0000

Data Index: 506972 (C4 (Web Text))

Max Activating Token Index: 1019

Text #11

Max Range: 1.4856. Min Range: -1.4856

Max Act: 0.8168. Min Act: -0.0000

Data Index: 850238 (C4 (Web Text))

Max Activating Token Index: 252

Text #12

Max Range: 1.4856. Min Range: -1.4856

Max Act: 0.8917. Min Act: -0.0000

Data Index: 510034 (C4 (Web Text))

Max Activating Token Index: 225

Text #13

Max Range: 1.4856. Min Range: -1.4856

Max Act: 0.8380. Min Act: -0.0000

Data Index: 396833 (C4 (Web Text))

Max Activating Token Index: 804

Text #14

Max Range: 1.4856. Min Range: -1.4856

Max Act: 0.7811. Min Act: -0.0000

Data Index: 919564 (C4 (Web Text))

Max Activating Token Index: 871

Text #15

Max Range: 1.4856. Min Range: -1.4856

Max Act: 0.8246. Min Act: -0.0000

Data Index: 831322 (C4 (Web Text))

Max Activating Token Index: 694

Text #16

Max Range: 1.4856. Min Range: -1.4856

Max Act: 0.8271. Min Act: -0.0000

Data Index: 500931 (C4 (Web Text))

Max Activating Token Index: 269

Text #17

Max Range: 1.4856. Min Range: -1.4856

Max Act: 0.7747. Min Act: -0.0000

Data Index: 1093317 (C4 (Web Text))

Max Activating Token Index: 414

Text #18

Max Range: 1.4856. Min Range: -1.4856

Max Act: 0.8252. Min Act: -0.0000

Data Index: 1248096 (C4 (Web Text))

Max Activating Token Index: 165

Text #19

Max Range: 1.4856. Min Range: -1.4856

Max Act: 0.7735. Min Act: -0.0000

Data Index: 138224 (C4 (Web Text))

Max Activating Token Index: 19