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

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

Neuron 4011 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1665. Min Range: -1.1665

Max Act: 1.1665. Min Act: -0.0000

Data Index: 1184038 (C4 (Web Text))

Max Activating Token Index: 435

Text #1

Max Range: 1.1665. Min Range: -1.1665

Max Act: 0.7728. Min Act: -0.0000

Data Index: 648172 (C4 (Web Text))

Max Activating Token Index: 771

Text #2

Max Range: 1.1665. Min Range: -1.1665

Max Act: 0.7806. Min Act: -0.0000

Data Index: 392567 (C4 (Web Text))

Max Activating Token Index: 561

Text #3

Max Range: 1.1665. Min Range: -1.1665

Max Act: 0.7279. Min Act: -0.0000

Data Index: 47874 (C4 (Web Text))

Max Activating Token Index: 185

Text #4

Max Range: 1.1665. Min Range: -1.1665

Max Act: 0.7414. Min Act: -0.0000

Data Index: 840115 (C4 (Web Text))

Max Activating Token Index: 483

Text #5

Max Range: 1.1665. Min Range: -1.1665

Max Act: 0.7142. Min Act: -0.0000

Data Index: 1400334 (Python Code)

Max Activating Token Index: 203

Text #6

Max Range: 1.1665. Min Range: -1.1665

Max Act: 0.7108. Min Act: -0.0000

Data Index: 807758 (C4 (Web Text))

Max Activating Token Index: 312

Text #7

Max Range: 1.1665. Min Range: -1.1665

Max Act: 0.7072. Min Act: -0.0000

Data Index: 92969 (C4 (Web Text))

Max Activating Token Index: 160

Text #8

Max Range: 1.1665. Min Range: -1.1665

Max Act: 0.7231. Min Act: -0.0000

Data Index: 1363316 (Python Code)

Max Activating Token Index: 820

Text #9

Max Range: 1.1665. Min Range: -1.1665

Max Act: 0.7424. Min Act: -0.0000

Data Index: 541377 (C4 (Web Text))

Max Activating Token Index: 479

Text #10

Max Range: 1.1665. Min Range: -1.1665

Max Act: 0.7014. Min Act: -0.0000

Data Index: 1170965 (C4 (Web Text))

Max Activating Token Index: 806

Text #11

Max Range: 1.1665. Min Range: -1.1665

Max Act: 0.7196. Min Act: -0.0000

Data Index: 120813 (C4 (Web Text))

Max Activating Token Index: 25

Text #12

Max Range: 1.1665. Min Range: -1.1665

Max Act: 0.7067. Min Act: -0.0000

Data Index: 1491118 (Python Code)

Max Activating Token Index: 246

Text #13

Max Range: 1.1665. Min Range: -1.1665

Max Act: 0.6887. Min Act: -0.0000

Data Index: 418114 (C4 (Web Text))

Max Activating Token Index: 385

Text #14

Max Range: 1.1665. Min Range: -1.1665

Max Act: 0.7296. Min Act: -0.0000

Data Index: 1096322 (C4 (Web Text))

Max Activating Token Index: 52

Text #15

Max Range: 1.1665. Min Range: -1.1665

Max Act: 0.7011. Min Act: -0.0000

Data Index: 696624 (C4 (Web Text))

Max Activating Token Index: 950

Text #16

Max Range: 1.1665. Min Range: -1.1665

Max Act: 0.7194. Min Act: -0.0000

Data Index: 560260 (C4 (Web Text))

Max Activating Token Index: 421

Text #17

Max Range: 1.1665. Min Range: -1.1665

Max Act: 0.6716. Min Act: -0.0000

Data Index: 784710 (C4 (Web Text))

Max Activating Token Index: 86

Text #18

Max Range: 1.1665. Min Range: -1.1665

Max Act: 0.7355. Min Act: -0.0000

Data Index: 1303729 (C4 (Web Text))

Max Activating Token Index: 154

Text #19

Max Range: 1.1665. Min Range: -1.1665

Max Act: 0.7242. Min Act: -0.0000

Data Index: 282684 (C4 (Web Text))

Max Activating Token Index: 833