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

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

Neuron 1273 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: 0.9884. Min Range: -0.9884

Max Act: 0.9884. Min Act: -0.0000

Data Index: 19115 (C4 (Web Text))

Max Activating Token Index: 530

Text #1

Max Range: 0.9884. Min Range: -0.9884

Max Act: 0.9129. Min Act: -0.0000

Data Index: 175848 (C4 (Web Text))

Max Activating Token Index: 644

Text #2

Max Range: 0.9884. Min Range: -0.9884

Max Act: 0.7728. Min Act: -0.0000

Data Index: 705383 (C4 (Web Text))

Max Activating Token Index: 362

Text #3

Max Range: 0.9884. Min Range: -0.9884

Max Act: 0.7052. Min Act: -0.0000

Data Index: 394989 (C4 (Web Text))

Max Activating Token Index: 116

Text #4

Max Range: 0.9884. Min Range: -0.9884

Max Act: 0.6758. Min Act: -0.0000

Data Index: 133538 (C4 (Web Text))

Max Activating Token Index: 869

Text #5

Max Range: 0.9884. Min Range: -0.9884

Max Act: 0.6904. Min Act: -0.0000

Data Index: 1294393 (C4 (Web Text))

Max Activating Token Index: 491

Text #6

Max Range: 0.9884. Min Range: -0.9884

Max Act: 0.6035. Min Act: -0.0000

Data Index: 176587 (C4 (Web Text))

Max Activating Token Index: 612

Text #7

Max Range: 0.9884. Min Range: -0.9884

Max Act: 0.6877. Min Act: -0.0000

Data Index: 522921 (C4 (Web Text))

Max Activating Token Index: 814

Text #8

Max Range: 0.9884. Min Range: -0.9884

Max Act: 0.7001. Min Act: -0.0000

Data Index: 193413 (C4 (Web Text))

Max Activating Token Index: 294

Text #9

Max Range: 0.9884. Min Range: -0.9884

Max Act: 0.7223. Min Act: -0.0000

Data Index: 235705 (C4 (Web Text))

Max Activating Token Index: 705

Text #10

Max Range: 0.9884. Min Range: -0.9884

Max Act: 0.6932. Min Act: -0.0000

Data Index: 928132 (C4 (Web Text))

Max Activating Token Index: 158

Text #11

Max Range: 0.9884. Min Range: -0.9884

Max Act: 0.6576. Min Act: -0.0000

Data Index: 684882 (C4 (Web Text))

Max Activating Token Index: 314

Text #12

Max Range: 0.9884. Min Range: -0.9884

Max Act: 0.6508. Min Act: -0.0000

Data Index: 759223 (C4 (Web Text))

Max Activating Token Index: 980

Text #13

Max Range: 0.9884. Min Range: -0.9884

Max Act: 0.6489. Min Act: -0.0000

Data Index: 563219 (C4 (Web Text))

Max Activating Token Index: 311

Text #14

Max Range: 0.9884. Min Range: -0.9884

Max Act: 0.6408. Min Act: -0.0000

Data Index: 210255 (C4 (Web Text))

Max Activating Token Index: 367

Text #15

Max Range: 0.9884. Min Range: -0.9884

Max Act: 0.6041. Min Act: -0.0000

Data Index: 1338166 (C4 (Web Text))

Max Activating Token Index: 250

Text #16

Max Range: 0.9884. Min Range: -0.9884

Max Act: 0.6516. Min Act: -0.0000

Data Index: 321049 (C4 (Web Text))

Max Activating Token Index: 133

Text #17

Max Range: 0.9884. Min Range: -0.9884

Max Act: 0.6291. Min Act: -0.0000

Data Index: 763121 (C4 (Web Text))

Max Activating Token Index: 154

Text #18

Max Range: 0.9884. Min Range: -0.9884

Max Act: 0.6509. Min Act: -0.0000

Data Index: 1264483 (C4 (Web Text))

Max Activating Token Index: 710

Text #19

Max Range: 0.9884. Min Range: -0.9884

Max Act: 0.5838. Min Act: -0.0000

Data Index: 48216 (C4 (Web Text))

Max Activating Token Index: 415