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

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

Neuron 4696 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3062. Min Range: -1.3062

Max Act: 1.3062. Min Act: -0.0000

Data Index: 972635 (C4 (Web Text))

Max Activating Token Index: 478

Text #1

Max Range: 1.3062. Min Range: -1.3062

Max Act: 1.1229. Min Act: -0.0000

Data Index: 1046208 (C4 (Web Text))

Max Activating Token Index: 371

Text #2

Max Range: 1.3062. Min Range: -1.3062

Max Act: 0.9151. Min Act: -0.0000

Data Index: 315813 (C4 (Web Text))

Max Activating Token Index: 749

Text #3

Max Range: 1.3062. Min Range: -1.3062

Max Act: 0.9281. Min Act: -0.0000

Data Index: 282124 (C4 (Web Text))

Max Activating Token Index: 400

Text #4

Max Range: 1.3062. Min Range: -1.3062

Max Act: 0.8048. Min Act: -0.0000

Data Index: 317765 (C4 (Web Text))

Max Activating Token Index: 172

Text #5

Max Range: 1.3062. Min Range: -1.3062

Max Act: 0.7495. Min Act: -0.0000

Data Index: 1262225 (C4 (Web Text))

Max Activating Token Index: 15

Text #6

Max Range: 1.3062. Min Range: -1.3062

Max Act: 0.7106. Min Act: -0.0000

Data Index: 280422 (C4 (Web Text))

Max Activating Token Index: 329

Text #7

Max Range: 1.3062. Min Range: -1.3062

Max Act: 0.7498. Min Act: -0.0000

Data Index: 136843 (C4 (Web Text))

Max Activating Token Index: 197

Text #8

Max Range: 1.3062. Min Range: -1.3062

Max Act: 0.7206. Min Act: -0.0000

Data Index: 914739 (C4 (Web Text))

Max Activating Token Index: 43

Text #9

Max Range: 1.3062. Min Range: -1.3062

Max Act: 0.7319. Min Act: -0.0000

Data Index: 1254370 (C4 (Web Text))

Max Activating Token Index: 130

Text #10

Max Range: 1.3062. Min Range: -1.3062

Max Act: 0.7141. Min Act: -0.0000

Data Index: 155723 (C4 (Web Text))

Max Activating Token Index: 681

Text #11

Max Range: 1.3062. Min Range: -1.3062

Max Act: 0.6798. Min Act: -0.0000

Data Index: 150876 (C4 (Web Text))

Max Activating Token Index: 680

Text #12

Max Range: 1.3062. Min Range: -1.3062

Max Act: 0.6620. Min Act: -0.0000

Data Index: 627630 (C4 (Web Text))

Max Activating Token Index: 798

Text #13

Max Range: 1.3062. Min Range: -1.3062

Max Act: 0.6335. Min Act: -0.0000

Data Index: 11679 (C4 (Web Text))

Max Activating Token Index: 375

Text #14

Max Range: 1.3062. Min Range: -1.3062

Max Act: 0.6738. Min Act: -0.0000

Data Index: 96355 (C4 (Web Text))

Max Activating Token Index: 331

Text #15

Max Range: 1.3062. Min Range: -1.3062

Max Act: 0.6743. Min Act: -0.0000

Data Index: 408631 (C4 (Web Text))

Max Activating Token Index: 819

Text #16

Max Range: 1.3062. Min Range: -1.3062

Max Act: 0.6504. Min Act: -0.0000

Data Index: 60972 (C4 (Web Text))

Max Activating Token Index: 281

Text #17

Max Range: 1.3062. Min Range: -1.3062

Max Act: 0.6502. Min Act: -0.0000

Data Index: 136081 (C4 (Web Text))

Max Activating Token Index: 551

Text #18

Max Range: 1.3062. Min Range: -1.3062

Max Act: 0.6277. Min Act: -0.0000

Data Index: 1124544 (C4 (Web Text))

Max Activating Token Index: 261

Text #19

Max Range: 1.3062. Min Range: -1.3062

Max Act: 0.6424. Min Act: -0.0000

Data Index: 663490 (C4 (Web Text))

Max Activating Token Index: 605