Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 72 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.7648. Min Range: -0.7648

Max Act: 0.7648. Min Act: -0.0006

Data Index: 779485 (C4 (Web Text))

Max Activating Token Index: 975

Text #1

Max Range: 0.7648. Min Range: -0.7648

Max Act: 0.7056. Min Act: -0.0006

Data Index: 129175 (C4 (Web Text))

Max Activating Token Index: 667

Text #2

Max Range: 0.7648. Min Range: -0.7648

Max Act: 0.7056. Min Act: -0.0006

Data Index: 658327 (C4 (Web Text))

Max Activating Token Index: 538

Text #3

Max Range: 0.7648. Min Range: -0.7648

Max Act: 0.7024. Min Act: -0.0006

Data Index: 599398 (C4 (Web Text))

Max Activating Token Index: 154

Text #4

Max Range: 0.7648. Min Range: -0.7648

Max Act: 0.7255. Min Act: -0.0006

Data Index: 1053930 (C4 (Web Text))

Max Activating Token Index: 153

Text #5

Max Range: 0.7648. Min Range: -0.7648

Max Act: 0.6655. Min Act: -0.0006

Data Index: 859346 (C4 (Web Text))

Max Activating Token Index: 859

Text #6

Max Range: 0.7648. Min Range: -0.7648

Max Act: 0.6850. Min Act: -0.0006

Data Index: 713380 (C4 (Web Text))

Max Activating Token Index: 381

Text #7

Max Range: 0.7648. Min Range: -0.7648

Max Act: 0.7223. Min Act: -0.0006

Data Index: 1273359 (C4 (Web Text))

Max Activating Token Index: 515

Text #8

Max Range: 0.7648. Min Range: -0.7648

Max Act: 0.6732. Min Act: -0.0006

Data Index: 1225382 (C4 (Web Text))

Max Activating Token Index: 195

Text #9

Max Range: 0.7648. Min Range: -0.7648

Max Act: 0.6718. Min Act: -0.0006

Data Index: 859926 (C4 (Web Text))

Max Activating Token Index: 557

Text #10

Max Range: 0.7648. Min Range: -0.7648

Max Act: 0.6287. Min Act: -0.0006

Data Index: 789340 (C4 (Web Text))

Max Activating Token Index: 628

Text #11

Max Range: 0.7648. Min Range: -0.7648

Max Act: 0.6857. Min Act: -0.0006

Data Index: 833615 (C4 (Web Text))

Max Activating Token Index: 721

Text #12

Max Range: 0.7648. Min Range: -0.7648

Max Act: 0.5996. Min Act: -0.0006

Data Index: 373989 (C4 (Web Text))

Max Activating Token Index: 312

Text #13

Max Range: 0.7648. Min Range: -0.7648

Max Act: 0.6190. Min Act: -0.0006

Data Index: 646545 (C4 (Web Text))

Max Activating Token Index: 900

Text #14

Max Range: 0.7648. Min Range: -0.7648

Max Act: 0.6776. Min Act: -0.0006

Data Index: 626401 (C4 (Web Text))

Max Activating Token Index: 931

Text #15

Max Range: 0.7648. Min Range: -0.7648

Max Act: 0.6301. Min Act: -0.0006

Data Index: 641524 (C4 (Web Text))

Max Activating Token Index: 34

Text #16

Max Range: 0.7648. Min Range: -0.7648

Max Act: 0.6506. Min Act: -0.0006

Data Index: 269393 (C4 (Web Text))

Max Activating Token Index: 86

Text #17

Max Range: 0.7648. Min Range: -0.7648

Max Act: 0.6258. Min Act: -0.0006

Data Index: 109923 (C4 (Web Text))

Max Activating Token Index: 537

Text #18

Max Range: 0.7648. Min Range: -0.7648

Max Act: 0.5816. Min Act: -0.0006

Data Index: 584471 (C4 (Web Text))

Max Activating Token Index: 704

Text #19

Max Range: 0.7648. Min Range: -0.7648

Max Act: 0.5985. Min Act: -0.0006

Data Index: 927083 (C4 (Web Text))

Max Activating Token Index: 701