Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 589 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.0109. Min Range: -1.0109

Max Act: 1.0109. Min Act: -0.0000

Data Index: 751001 (C4 (Web Text))

Max Activating Token Index: 322

Text #1

Max Range: 1.0109. Min Range: -1.0109

Max Act: 0.9358. Min Act: -0.0000

Data Index: 203155 (C4 (Web Text))

Max Activating Token Index: 148

Text #2

Max Range: 1.0109. Min Range: -1.0109

Max Act: 0.9000. Min Act: -0.0000

Data Index: 497532 (C4 (Web Text))

Max Activating Token Index: 676

Text #3

Max Range: 1.0109. Min Range: -1.0109

Max Act: 0.8491. Min Act: -0.0000

Data Index: 313564 (C4 (Web Text))

Max Activating Token Index: 823

Text #4

Max Range: 1.0109. Min Range: -1.0109

Max Act: 0.7665. Min Act: -0.0000

Data Index: 548492 (C4 (Web Text))

Max Activating Token Index: 743

Text #5

Max Range: 1.0109. Min Range: -1.0109

Max Act: 0.7925. Min Act: -0.0000

Data Index: 514355 (C4 (Web Text))

Max Activating Token Index: 41

Text #6

Max Range: 1.0109. Min Range: -1.0109

Max Act: 0.7885. Min Act: -0.0000

Data Index: 312355 (C4 (Web Text))

Max Activating Token Index: 401

Text #7

Max Range: 1.0109. Min Range: -1.0109

Max Act: 0.7207. Min Act: -0.0000

Data Index: 171974 (C4 (Web Text))

Max Activating Token Index: 951

Text #8

Max Range: 1.0109. Min Range: -1.0109

Max Act: 0.7530. Min Act: -0.0001

Data Index: 239329 (C4 (Web Text))

Max Activating Token Index: 917

Text #9

Max Range: 1.0109. Min Range: -1.0109

Max Act: 0.7459. Min Act: -0.0000

Data Index: 350821 (C4 (Web Text))

Max Activating Token Index: 72

Text #10

Max Range: 1.0109. Min Range: -1.0109

Max Act: 0.8407. Min Act: -0.0000

Data Index: 929086 (C4 (Web Text))

Max Activating Token Index: 845

Text #11

Max Range: 1.0109. Min Range: -1.0109

Max Act: 0.7463. Min Act: -0.0000

Data Index: 443786 (C4 (Web Text))

Max Activating Token Index: 42

Text #12

Max Range: 1.0109. Min Range: -1.0109

Max Act: 0.7632. Min Act: -0.0000

Data Index: 503366 (C4 (Web Text))

Max Activating Token Index: 641

Text #13

Max Range: 1.0109. Min Range: -1.0109

Max Act: 0.7426. Min Act: -0.0000

Data Index: 212505 (C4 (Web Text))

Max Activating Token Index: 105

Text #14

Max Range: 1.0109. Min Range: -1.0109

Max Act: 0.7329. Min Act: -0.0000

Data Index: 366876 (C4 (Web Text))

Max Activating Token Index: 236

Text #15

Max Range: 1.0109. Min Range: -1.0109

Max Act: 0.7291. Min Act: -0.0000

Data Index: 91114 (C4 (Web Text))

Max Activating Token Index: 720

Text #16

Max Range: 1.0109. Min Range: -1.0109

Max Act: 0.7353. Min Act: -0.0000

Data Index: 103257 (C4 (Web Text))

Max Activating Token Index: 135

Text #17

Max Range: 1.0109. Min Range: -1.0109

Max Act: 0.6899. Min Act: -0.0000

Data Index: 199913 (C4 (Web Text))

Max Activating Token Index: 968

Text #18

Max Range: 1.0109. Min Range: -1.0109

Max Act: 0.7143. Min Act: -0.0000

Data Index: 328222 (C4 (Web Text))

Max Activating Token Index: 284

Text #19

Max Range: 1.0109. Min Range: -1.0109

Max Act: 0.6603. Min Act: -0.0000

Data Index: 480210 (C4 (Web Text))

Max Activating Token Index: 130