Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 650 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0686. Min Act: -0.0001

Data Index: 353221 (C4 (Web Text))

Max Activating Token Index: 34

Text #1

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0518. Min Act: -0.0001

Data Index: 323860 (C4 (Web Text))

Max Activating Token Index: 822

Text #2

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0570. Min Act: -0.0001

Data Index: 134314 (C4 (Web Text))

Max Activating Token Index: 745

Text #3

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0537. Min Act: -0.0000

Data Index: 1258523 (C4 (Web Text))

Max Activating Token Index: 948

Text #4

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0533. Min Act: -0.0001

Data Index: 1199491 (C4 (Web Text))

Max Activating Token Index: 84

Text #5

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0532. Min Act: -0.0001

Data Index: 268781 (C4 (Web Text))

Max Activating Token Index: 142

Text #6

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0530. Min Act: -0.0001

Data Index: 1461252 (Python Code)

Max Activating Token Index: 18

Text #7

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0548. Min Act: -0.0001

Data Index: 793202 (C4 (Web Text))

Max Activating Token Index: 63

Text #8

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0499. Min Act: -0.0000

Data Index: 882975 (C4 (Web Text))

Max Activating Token Index: 876

Text #9

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0526. Min Act: -0.0001

Data Index: 1014425 (C4 (Web Text))

Max Activating Token Index: 971

Text #10

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0525. Min Act: -0.0001

Data Index: 730223 (C4 (Web Text))

Max Activating Token Index: 109

Text #11

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0550. Min Act: -0.0000

Data Index: 2658 (C4 (Web Text))

Max Activating Token Index: 323

Text #12

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0473. Min Act: -0.0001

Data Index: 723091 (C4 (Web Text))

Max Activating Token Index: 178

Text #13

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0506. Min Act: -0.0001

Data Index: 415062 (C4 (Web Text))

Max Activating Token Index: 844

Text #14

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0515. Min Act: -0.0001

Data Index: 643199 (C4 (Web Text))

Max Activating Token Index: 929

Text #15

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0519. Min Act: -0.0001

Data Index: 297274 (C4 (Web Text))

Max Activating Token Index: 595

Text #16

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0504. Min Act: -0.0001

Data Index: 1278416 (C4 (Web Text))

Max Activating Token Index: 970

Text #17

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0504. Min Act: -0.0001

Data Index: 309543 (C4 (Web Text))

Max Activating Token Index: 829

Text #18

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0507. Min Act: -0.0001

Data Index: 1462321 (Python Code)

Max Activating Token Index: 140

Text #19

Max Range: 0.0686. Min Range: -0.0686

Max Act: 0.0500. Min Act: -0.0000

Data Index: 578335 (C4 (Web Text))

Max Activating Token Index: 156