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

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

Neuron 3236 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: 0.7556. Min Range: -0.7556

Max Act: 0.7556. Min Act: -0.0000

Data Index: 1277429 (C4 (Web Text))

Max Activating Token Index: 689

Text #1

Max Range: 0.7556. Min Range: -0.7556

Max Act: 0.6675. Min Act: -0.0000

Data Index: 498300 (C4 (Web Text))

Max Activating Token Index: 168

Text #2

Max Range: 0.7556. Min Range: -0.7556

Max Act: 0.6523. Min Act: -0.0000

Data Index: 861785 (C4 (Web Text))

Max Activating Token Index: 1021

Text #3

Max Range: 0.7556. Min Range: -0.7556

Max Act: 0.5752. Min Act: -0.0000

Data Index: 131065 (C4 (Web Text))

Max Activating Token Index: 547

Text #4

Max Range: 0.7556. Min Range: -0.7556

Max Act: 0.6750. Min Act: -0.0000

Data Index: 29042 (C4 (Web Text))

Max Activating Token Index: 743

Text #5

Max Range: 0.7556. Min Range: -0.7556

Max Act: 0.4372. Min Act: -0.0000

Data Index: 350176 (C4 (Web Text))

Max Activating Token Index: 829

Text #6

Max Range: 0.7556. Min Range: -0.7556

Max Act: 0.5538. Min Act: -0.0000

Data Index: 573023 (C4 (Web Text))

Max Activating Token Index: 906

Text #7

Max Range: 0.7556. Min Range: -0.7556

Max Act: 0.5461. Min Act: -0.0000

Data Index: 1298203 (C4 (Web Text))

Max Activating Token Index: 790

Text #8

Max Range: 0.7556. Min Range: -0.7556

Max Act: 0.5503. Min Act: -0.0000

Data Index: 1061280 (C4 (Web Text))

Max Activating Token Index: 224

Text #9

Max Range: 0.7556. Min Range: -0.7556

Max Act: 0.5676. Min Act: -0.0000

Data Index: 51075 (C4 (Web Text))

Max Activating Token Index: 592

Text #10

Max Range: 0.7556. Min Range: -0.7556

Max Act: 0.4807. Min Act: -0.0000

Data Index: 669064 (C4 (Web Text))

Max Activating Token Index: 625

Text #11

Max Range: 0.7556. Min Range: -0.7556

Max Act: 0.5061. Min Act: -0.0000

Data Index: 1048297 (C4 (Web Text))

Max Activating Token Index: 725

Text #12

Max Range: 0.7556. Min Range: -0.7556

Max Act: 0.4936. Min Act: -0.0000

Data Index: 440017 (C4 (Web Text))

Max Activating Token Index: 508

Text #13

Max Range: 0.7556. Min Range: -0.7556

Max Act: 0.5099. Min Act: -0.0000

Data Index: 789705 (C4 (Web Text))

Max Activating Token Index: 850

Text #14

Max Range: 0.7556. Min Range: -0.7556

Max Act: 0.5094. Min Act: -0.0000

Data Index: 389490 (C4 (Web Text))

Max Activating Token Index: 712

Text #15

Max Range: 0.7556. Min Range: -0.7556

Max Act: 0.4973. Min Act: -0.0000

Data Index: 381595 (C4 (Web Text))

Max Activating Token Index: 994

Text #16

Max Range: 0.7556. Min Range: -0.7556

Max Act: 0.4632. Min Act: -0.0000

Data Index: 199104 (C4 (Web Text))

Max Activating Token Index: 524

Text #17

Max Range: 0.7556. Min Range: -0.7556

Max Act: 0.4569. Min Act: -0.0000

Data Index: 842173 (C4 (Web Text))

Max Activating Token Index: 696

Text #18

Max Range: 0.7556. Min Range: -0.7556

Max Act: 0.4335. Min Act: -0.0000

Data Index: 1030512 (C4 (Web Text))

Max Activating Token Index: 703

Text #19

Max Range: 0.7556. Min Range: -0.7556

Max Act: 0.4399. Min Act: -0.0000

Data Index: 389906 (C4 (Web Text))

Max Activating Token Index: 805