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

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

Neuron 4501 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1065. Min Range: -1.1065

Max Act: 1.1065. Min Act: -0.0000

Data Index: 1332714 (C4 (Web Text))

Max Activating Token Index: 664

Text #1

Max Range: 1.1065. Min Range: -1.1065

Max Act: 0.6953. Min Act: -0.0000

Data Index: 1159492 (C4 (Web Text))

Max Activating Token Index: 414

Text #2

Max Range: 1.1065. Min Range: -1.1065

Max Act: 0.7095. Min Act: -0.0000

Data Index: 437417 (C4 (Web Text))

Max Activating Token Index: 478

Text #3

Max Range: 1.1065. Min Range: -1.1065

Max Act: 0.6653. Min Act: -0.0000

Data Index: 12733 (C4 (Web Text))

Max Activating Token Index: 197

Text #4

Max Range: 1.1065. Min Range: -1.1065

Max Act: 0.7152. Min Act: -0.0000

Data Index: 571076 (C4 (Web Text))

Max Activating Token Index: 822

Text #5

Max Range: 1.1065. Min Range: -1.1065

Max Act: 0.6342. Min Act: -0.0000

Data Index: 419854 (C4 (Web Text))

Max Activating Token Index: 123

Text #6

Max Range: 1.1065. Min Range: -1.1065

Max Act: 0.6387. Min Act: -0.0000

Data Index: 802490 (C4 (Web Text))

Max Activating Token Index: 106

Text #7

Max Range: 1.1065. Min Range: -1.1065

Max Act: 0.6497. Min Act: -0.0000

Data Index: 32370 (C4 (Web Text))

Max Activating Token Index: 106

Text #8

Max Range: 1.1065. Min Range: -1.1065

Max Act: 0.6649. Min Act: -0.0000

Data Index: 371946 (C4 (Web Text))

Max Activating Token Index: 771

Text #9

Max Range: 1.1065. Min Range: -1.1065

Max Act: 0.6043. Min Act: -0.0000

Data Index: 1267176 (C4 (Web Text))

Max Activating Token Index: 948

Text #10

Max Range: 1.1065. Min Range: -1.1065

Max Act: 0.6231. Min Act: -0.0000

Data Index: 108286 (C4 (Web Text))

Max Activating Token Index: 741

Text #11

Max Range: 1.1065. Min Range: -1.1065

Max Act: 0.5885. Min Act: -0.0000

Data Index: 587625 (C4 (Web Text))

Max Activating Token Index: 260

Text #12

Max Range: 1.1065. Min Range: -1.1065

Max Act: 0.6451. Min Act: -0.0000

Data Index: 690255 (C4 (Web Text))

Max Activating Token Index: 970

Text #13

Max Range: 1.1065. Min Range: -1.1065

Max Act: 0.6531. Min Act: -0.0000

Data Index: 710792 (C4 (Web Text))

Max Activating Token Index: 301

Text #14

Max Range: 1.1065. Min Range: -1.1065

Max Act: 0.5513. Min Act: -0.0000

Data Index: 386465 (C4 (Web Text))

Max Activating Token Index: 220

Text #15

Max Range: 1.1065. Min Range: -1.1065

Max Act: 0.6435. Min Act: -0.0000

Data Index: 750663 (C4 (Web Text))

Max Activating Token Index: 103

Text #16

Max Range: 1.1065. Min Range: -1.1065

Max Act: 0.6001. Min Act: -0.0000

Data Index: 309650 (C4 (Web Text))

Max Activating Token Index: 146

Text #17

Max Range: 1.1065. Min Range: -1.1065

Max Act: 0.6193. Min Act: -0.0000

Data Index: 1338416 (C4 (Web Text))

Max Activating Token Index: 470

Text #18

Max Range: 1.1065. Min Range: -1.1065

Max Act: 0.6141. Min Act: -0.0000

Data Index: 202245 (C4 (Web Text))

Max Activating Token Index: 571

Text #19

Max Range: 1.1065. Min Range: -1.1065

Max Act: 0.5879. Min Act: -0.0000

Data Index: 268289 (C4 (Web Text))

Max Activating Token Index: 747