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

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

Neuron 4798 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4800. Min Range: -2.4800

Max Act: 2.3377. Min Act: -0.0000

Data Index: 418698 (C4 (Web Text))

Max Activating Token Index: 137

Text #1

Max Range: 2.4800. Min Range: -2.4800

Max Act: 2.4800. Min Act: -0.0000

Data Index: 281134 (C4 (Web Text))

Max Activating Token Index: 179

Text #2

Max Range: 2.4800. Min Range: -2.4800

Max Act: 2.4587. Min Act: -0.0000

Data Index: 1084212 (C4 (Web Text))

Max Activating Token Index: 742

Text #3

Max Range: 2.4800. Min Range: -2.4800

Max Act: 2.2733. Min Act: -0.0000

Data Index: 411811 (C4 (Web Text))

Max Activating Token Index: 273

Text #4

Max Range: 2.4800. Min Range: -2.4800

Max Act: 2.2885. Min Act: -0.0000

Data Index: 796914 (C4 (Web Text))

Max Activating Token Index: 481

Text #5

Max Range: 2.4800. Min Range: -2.4800

Max Act: 2.2013. Min Act: -0.0000

Data Index: 583506 (C4 (Web Text))

Max Activating Token Index: 813

Text #6

Max Range: 2.4800. Min Range: -2.4800

Max Act: 2.0579. Min Act: -0.0000

Data Index: 1331555 (C4 (Web Text))

Max Activating Token Index: 937

Text #7

Max Range: 2.4800. Min Range: -2.4800

Max Act: 2.1576. Min Act: -0.0000

Data Index: 627687 (C4 (Web Text))

Max Activating Token Index: 861

Text #8

Max Range: 2.4800. Min Range: -2.4800

Max Act: 2.0484. Min Act: -0.0000

Data Index: 1041663 (C4 (Web Text))

Max Activating Token Index: 221

Text #9

Max Range: 2.4800. Min Range: -2.4800

Max Act: 2.0436. Min Act: -0.0000

Data Index: 45941 (C4 (Web Text))

Max Activating Token Index: 457

Text #10

Max Range: 2.4800. Min Range: -2.4800

Max Act: 2.0178. Min Act: -0.0000

Data Index: 517836 (C4 (Web Text))

Max Activating Token Index: 716

Text #11

Max Range: 2.4800. Min Range: -2.4800

Max Act: 2.1879. Min Act: -0.0000

Data Index: 610072 (C4 (Web Text))

Max Activating Token Index: 973

Text #12

Max Range: 2.4800. Min Range: -2.4800

Max Act: 1.9563. Min Act: -0.0000

Data Index: 150823 (C4 (Web Text))

Max Activating Token Index: 515

Text #13

Max Range: 2.4800. Min Range: -2.4800

Max Act: 2.0107. Min Act: -0.0000

Data Index: 480606 (C4 (Web Text))

Max Activating Token Index: 361

Text #14

Max Range: 2.4800. Min Range: -2.4800

Max Act: 1.8142. Min Act: -0.0000

Data Index: 1094023 (C4 (Web Text))

Max Activating Token Index: 593

Text #15

Max Range: 2.4800. Min Range: -2.4800

Max Act: 1.7839. Min Act: -0.0000

Data Index: 557267 (C4 (Web Text))

Max Activating Token Index: 776

Text #16

Max Range: 2.4800. Min Range: -2.4800

Max Act: 1.7696. Min Act: -0.0000

Data Index: 943830 (C4 (Web Text))

Max Activating Token Index: 660

Text #17

Max Range: 2.4800. Min Range: -2.4800

Max Act: 1.8651. Min Act: -0.0000

Data Index: 788095 (C4 (Web Text))

Max Activating Token Index: 369

Text #18

Max Range: 2.4800. Min Range: -2.4800

Max Act: 1.8481. Min Act: -0.0000

Data Index: 1311247 (C4 (Web Text))

Max Activating Token Index: 146

Text #19

Max Range: 2.4800. Min Range: -2.4800

Max Act: 1.7232. Min Act: -0.0000

Data Index: 272314 (C4 (Web Text))

Max Activating Token Index: 490