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

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

Neuron 4982 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8770. Min Range: -1.8770

Max Act: 1.8770. Min Act: -0.0000

Data Index: 934610 (C4 (Web Text))

Max Activating Token Index: 854

Text #1

Max Range: 1.8770. Min Range: -1.8770

Max Act: 1.2781. Min Act: -0.0000

Data Index: 622554 (C4 (Web Text))

Max Activating Token Index: 23

Text #2

Max Range: 1.8770. Min Range: -1.8770

Max Act: 1.1835. Min Act: -0.0000

Data Index: 756139 (C4 (Web Text))

Max Activating Token Index: 349

Text #3

Max Range: 1.8770. Min Range: -1.8770

Max Act: 1.2000. Min Act: -0.0000

Data Index: 182558 (C4 (Web Text))

Max Activating Token Index: 639

Text #4

Max Range: 1.8770. Min Range: -1.8770

Max Act: 1.1914. Min Act: -0.0000

Data Index: 201287 (C4 (Web Text))

Max Activating Token Index: 519

Text #5

Max Range: 1.8770. Min Range: -1.8770

Max Act: 1.0943. Min Act: -0.0000

Data Index: 1315499 (C4 (Web Text))

Max Activating Token Index: 193

Text #6

Max Range: 1.8770. Min Range: -1.8770

Max Act: 1.0131. Min Act: -0.0000

Data Index: 848923 (C4 (Web Text))

Max Activating Token Index: 240

Text #7

Max Range: 1.8770. Min Range: -1.8770

Max Act: 1.0993. Min Act: -0.0000

Data Index: 95358 (C4 (Web Text))

Max Activating Token Index: 222

Text #8

Max Range: 1.8770. Min Range: -1.8770

Max Act: 1.1179. Min Act: -0.0000

Data Index: 960010 (C4 (Web Text))

Max Activating Token Index: 526

Text #9

Max Range: 1.8770. Min Range: -1.8770

Max Act: 1.0380. Min Act: -0.0000

Data Index: 1041451 (C4 (Web Text))

Max Activating Token Index: 18

Text #10

Max Range: 1.8770. Min Range: -1.8770

Max Act: 1.0206. Min Act: -0.0000

Data Index: 185486 (C4 (Web Text))

Max Activating Token Index: 214

Text #11

Max Range: 1.8770. Min Range: -1.8770

Max Act: 0.9507. Min Act: -0.0000

Data Index: 977788 (C4 (Web Text))

Max Activating Token Index: 823

Text #12

Max Range: 1.8770. Min Range: -1.8770

Max Act: 0.9518. Min Act: -0.0000

Data Index: 948055 (C4 (Web Text))

Max Activating Token Index: 128

Text #13

Max Range: 1.8770. Min Range: -1.8770

Max Act: 0.9409. Min Act: -0.0000

Data Index: 601597 (C4 (Web Text))

Max Activating Token Index: 374

Text #14

Max Range: 1.8770. Min Range: -1.8770

Max Act: 0.8781. Min Act: -0.0000

Data Index: 350913 (C4 (Web Text))

Max Activating Token Index: 214

Text #15

Max Range: 1.8770. Min Range: -1.8770

Max Act: 0.8590. Min Act: -0.0000

Data Index: 943066 (C4 (Web Text))

Max Activating Token Index: 432

Text #16

Max Range: 1.8770. Min Range: -1.8770

Max Act: 0.9031. Min Act: -0.0000

Data Index: 327629 (C4 (Web Text))

Max Activating Token Index: 720

Text #17

Max Range: 1.8770. Min Range: -1.8770

Max Act: 0.8373. Min Act: -0.0000

Data Index: 543125 (C4 (Web Text))

Max Activating Token Index: 280

Text #18

Max Range: 1.8770. Min Range: -1.8770

Max Act: 0.8647. Min Act: -0.0000

Data Index: 600964 (C4 (Web Text))

Max Activating Token Index: 701

Text #19

Max Range: 1.8770. Min Range: -1.8770

Max Act: 0.8905. Min Act: -0.0000

Data Index: 1210612 (C4 (Web Text))

Max Activating Token Index: 383