Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 350 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.7248. Min Range: -0.7248

Max Act: 0.7248. Min Act: -0.0001

Data Index: 1432897 (Python Code)

Max Activating Token Index: 364

Text #1

Max Range: 0.7248. Min Range: -0.7248

Max Act: 0.6626. Min Act: -0.0002

Data Index: 1582479 (Python Code)

Max Activating Token Index: 601

Text #2

Max Range: 0.7248. Min Range: -0.7248

Max Act: 0.6498. Min Act: -0.0001

Data Index: 1443266 (Python Code)

Max Activating Token Index: 178

Text #3

Max Range: 0.7248. Min Range: -0.7248

Max Act: 0.6288. Min Act: -0.0001

Data Index: 1541973 (Python Code)

Max Activating Token Index: 555

Text #4

Max Range: 0.7248. Min Range: -0.7248

Max Act: 0.6568. Min Act: -0.0001

Data Index: 1443848 (Python Code)

Max Activating Token Index: 769

Text #5

Max Range: 0.7248. Min Range: -0.7248

Max Act: 0.5997. Min Act: -0.0001

Data Index: 1540802 (Python Code)

Max Activating Token Index: 178

Text #6

Max Range: 0.7248. Min Range: -0.7248

Max Act: 0.6127. Min Act: -0.0001

Data Index: 1533644 (Python Code)

Max Activating Token Index: 102

Text #7

Max Range: 0.7248. Min Range: -0.7248

Max Act: 0.5751. Min Act: -0.0001

Data Index: 1566320 (Python Code)

Max Activating Token Index: 996

Text #8

Max Range: 0.7248. Min Range: -0.7248

Max Act: 0.5745. Min Act: -0.0001

Data Index: 1582427 (Python Code)

Max Activating Token Index: 455

Text #9

Max Range: 0.7248. Min Range: -0.7248

Max Act: 0.5499. Min Act: -0.0001

Data Index: 1458519 (Python Code)

Max Activating Token Index: 780

Text #10

Max Range: 0.7248. Min Range: -0.7248

Max Act: 0.6009. Min Act: -0.0001

Data Index: 1510857 (Python Code)

Max Activating Token Index: 642

Text #11

Max Range: 0.7248. Min Range: -0.7248

Max Act: 0.5765. Min Act: -0.0002

Data Index: 1455096 (Python Code)

Max Activating Token Index: 696

Text #12

Max Range: 0.7248. Min Range: -0.7248

Max Act: 0.5890. Min Act: -0.0001

Data Index: 1401612 (Python Code)

Max Activating Token Index: 955

Text #13

Max Range: 0.7248. Min Range: -0.7248

Max Act: 0.5773. Min Act: -0.0001

Data Index: 1435883 (Python Code)

Max Activating Token Index: 657

Text #14

Max Range: 0.7248. Min Range: -0.7248

Max Act: 0.5584. Min Act: -0.0002

Data Index: 1415610 (Python Code)

Max Activating Token Index: 209

Text #15

Max Range: 0.7248. Min Range: -0.7248

Max Act: 0.5841. Min Act: -0.0001

Data Index: 1631296 (Python Code)

Max Activating Token Index: 1012

Text #16

Max Range: 0.7248. Min Range: -0.7248

Max Act: 0.6038. Min Act: -0.0001

Data Index: 1360936 (Python Code)

Max Activating Token Index: 1015

Text #17

Max Range: 0.7248. Min Range: -0.7248

Max Act: 0.5668. Min Act: -0.0001

Data Index: 1515522 (Python Code)

Max Activating Token Index: 451

Text #18

Max Range: 0.7248. Min Range: -0.7248

Max Act: 0.5621. Min Act: -0.0001

Data Index: 1640293 (Python Code)

Max Activating Token Index: 634

Text #19

Max Range: 0.7248. Min Range: -0.7248

Max Act: 0.5767. Min Act: -0.0001

Data Index: 1433283 (Python Code)

Max Activating Token Index: 343