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

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

Neuron 3690 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: 2.1554. Min Range: -2.1554

Max Act: 2.1376. Min Act: -0.0000

Data Index: 530988 (C4 (Web Text))

Max Activating Token Index: 521

Text #1

Max Range: 2.1554. Min Range: -2.1554

Max Act: 2.1554. Min Act: -0.0000

Data Index: 1206237 (C4 (Web Text))

Max Activating Token Index: 303

Text #2

Max Range: 2.1554. Min Range: -2.1554

Max Act: 2.0534. Min Act: -0.0000

Data Index: 983282 (C4 (Web Text))

Max Activating Token Index: 403

Text #3

Max Range: 2.1554. Min Range: -2.1554

Max Act: 2.0220. Min Act: -0.0000

Data Index: 870808 (C4 (Web Text))

Max Activating Token Index: 38

Text #4

Max Range: 2.1554. Min Range: -2.1554

Max Act: 2.0050. Min Act: -0.0000

Data Index: 1253237 (C4 (Web Text))

Max Activating Token Index: 106

Text #5

Max Range: 2.1554. Min Range: -2.1554

Max Act: 2.1278. Min Act: -0.0000

Data Index: 39774 (C4 (Web Text))

Max Activating Token Index: 891

Text #6

Max Range: 2.1554. Min Range: -2.1554

Max Act: 2.0002. Min Act: -0.0000

Data Index: 420131 (C4 (Web Text))

Max Activating Token Index: 252

Text #7

Max Range: 2.1554. Min Range: -2.1554

Max Act: 2.0379. Min Act: -0.0000

Data Index: 597559 (C4 (Web Text))

Max Activating Token Index: 789

Text #8

Max Range: 2.1554. Min Range: -2.1554

Max Act: 1.9768. Min Act: -0.0000

Data Index: 802771 (C4 (Web Text))

Max Activating Token Index: 417

Text #9

Max Range: 2.1554. Min Range: -2.1554

Max Act: 1.9721. Min Act: -0.0000

Data Index: 757264 (C4 (Web Text))

Max Activating Token Index: 29

Text #10

Max Range: 2.1554. Min Range: -2.1554

Max Act: 2.0625. Min Act: -0.0000

Data Index: 979821 (C4 (Web Text))

Max Activating Token Index: 727

Text #11

Max Range: 2.1554. Min Range: -2.1554

Max Act: 1.9494. Min Act: -0.0000

Data Index: 1039008 (C4 (Web Text))

Max Activating Token Index: 238

Text #12

Max Range: 2.1554. Min Range: -2.1554

Max Act: 1.9950. Min Act: -0.0000

Data Index: 1107627 (C4 (Web Text))

Max Activating Token Index: 586

Text #13

Max Range: 2.1554. Min Range: -2.1554

Max Act: 1.8991. Min Act: -0.0000

Data Index: 704790 (C4 (Web Text))

Max Activating Token Index: 818

Text #14

Max Range: 2.1554. Min Range: -2.1554

Max Act: 1.8319. Min Act: -0.0000

Data Index: 811122 (C4 (Web Text))

Max Activating Token Index: 370

Text #15

Max Range: 2.1554. Min Range: -2.1554

Max Act: 1.9959. Min Act: -0.0000

Data Index: 307909 (C4 (Web Text))

Max Activating Token Index: 856

Text #16

Max Range: 2.1554. Min Range: -2.1554

Max Act: 1.8683. Min Act: -0.0000

Data Index: 637742 (C4 (Web Text))

Max Activating Token Index: 1012

Text #17

Max Range: 2.1554. Min Range: -2.1554

Max Act: 1.8844. Min Act: -0.0000

Data Index: 868358 (C4 (Web Text))

Max Activating Token Index: 1002

Text #18

Max Range: 2.1554. Min Range: -2.1554

Max Act: 1.7679. Min Act: -0.0000

Data Index: 1072082 (C4 (Web Text))

Max Activating Token Index: 143

Text #19

Max Range: 2.1554. Min Range: -2.1554

Max Act: 1.8611. Min Act: -0.0000

Data Index: 1321177 (C4 (Web Text))

Max Activating Token Index: 902