Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 23 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.9720. Min Range: -0.9720

Max Act: 0.9720. Min Act: -0.0000

Data Index: 1621209 (Python Code)

Max Activating Token Index: 397

Text #1

Max Range: 0.9720. Min Range: -0.9720

Max Act: 0.9475. Min Act: -0.0000

Data Index: 1416543 (Python Code)

Max Activating Token Index: 871

Text #2

Max Range: 0.9720. Min Range: -0.9720

Max Act: 0.8151. Min Act: -0.0000

Data Index: 753689 (C4 (Web Text))

Max Activating Token Index: 675

Text #3

Max Range: 0.9720. Min Range: -0.9720

Max Act: 0.6891. Min Act: -0.0000

Data Index: 473312 (C4 (Web Text))

Max Activating Token Index: 192

Text #4

Max Range: 0.9720. Min Range: -0.9720

Max Act: 0.7548. Min Act: -0.0000

Data Index: 368128 (C4 (Web Text))

Max Activating Token Index: 459

Text #5

Max Range: 0.9720. Min Range: -0.9720

Max Act: 0.7613. Min Act: -0.0000

Data Index: 1264614 (C4 (Web Text))

Max Activating Token Index: 459

Text #6

Max Range: 0.9720. Min Range: -0.9720

Max Act: 0.7033. Min Act: -0.0000

Data Index: 329366 (C4 (Web Text))

Max Activating Token Index: 174

Text #7

Max Range: 0.9720. Min Range: -0.9720

Max Act: 0.6784. Min Act: -0.0000

Data Index: 1332228 (C4 (Web Text))

Max Activating Token Index: 467

Text #8

Max Range: 0.9720. Min Range: -0.9720

Max Act: 0.7028. Min Act: -0.0000

Data Index: 556047 (C4 (Web Text))

Max Activating Token Index: 769

Text #9

Max Range: 0.9720. Min Range: -0.9720

Max Act: 0.7112. Min Act: -0.0000

Data Index: 116443 (C4 (Web Text))

Max Activating Token Index: 856

Text #10

Max Range: 0.9720. Min Range: -0.9720

Max Act: 0.6239. Min Act: -0.0000

Data Index: 1209461 (C4 (Web Text))

Max Activating Token Index: 731

Text #11

Max Range: 0.9720. Min Range: -0.9720

Max Act: 0.6246. Min Act: -0.0000

Data Index: 1365476 (Python Code)

Max Activating Token Index: 158

Text #12

Max Range: 0.9720. Min Range: -0.9720

Max Act: 0.5697. Min Act: -0.0000

Data Index: 11764 (C4 (Web Text))

Max Activating Token Index: 645

Text #13

Max Range: 0.9720. Min Range: -0.9720

Max Act: 0.7208. Min Act: -0.0000

Data Index: 1578727 (Python Code)

Max Activating Token Index: 839

Text #14

Max Range: 0.9720. Min Range: -0.9720

Max Act: 0.6244. Min Act: -0.0000

Data Index: 1168273 (C4 (Web Text))

Max Activating Token Index: 891

Text #15

Max Range: 0.9720. Min Range: -0.9720

Max Act: 0.6051. Min Act: -0.0000

Data Index: 1170566 (C4 (Web Text))

Max Activating Token Index: 240

Text #16

Max Range: 0.9720. Min Range: -0.9720

Max Act: 0.6422. Min Act: -0.0000

Data Index: 1555149 (Python Code)

Max Activating Token Index: 261

Text #17

Max Range: 0.9720. Min Range: -0.9720

Max Act: 0.5197. Min Act: -0.0000

Data Index: 1554014 (Python Code)

Max Activating Token Index: 659

Text #18

Max Range: 0.9720. Min Range: -0.9720

Max Act: 0.5830. Min Act: -0.0000

Data Index: 286496 (C4 (Web Text))

Max Activating Token Index: 719

Text #19

Max Range: 0.9720. Min Range: -0.9720

Max Act: 0.5409. Min Act: -0.0000

Data Index: 1459872 (Python Code)

Max Activating Token Index: 546