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

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

Neuron 478 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: 0.8855. Min Range: -0.8855

Max Act: 0.8855. Min Act: -0.0001

Data Index: 973595 (C4 (Web Text))

Max Activating Token Index: 593

Text #1

Max Range: 0.8855. Min Range: -0.8855

Max Act: 0.8759. Min Act: -0.0001

Data Index: 703381 (C4 (Web Text))

Max Activating Token Index: 584

Text #2

Max Range: 0.8855. Min Range: -0.8855

Max Act: 0.8129. Min Act: -0.0001

Data Index: 647924 (C4 (Web Text))

Max Activating Token Index: 799

Text #3

Max Range: 0.8855. Min Range: -0.8855

Max Act: 0.7615. Min Act: -0.0001

Data Index: 132430 (C4 (Web Text))

Max Activating Token Index: 314

Text #4

Max Range: 0.8855. Min Range: -0.8855

Max Act: 0.8087. Min Act: -0.0001

Data Index: 112338 (C4 (Web Text))

Max Activating Token Index: 347

Text #5

Max Range: 0.8855. Min Range: -0.8855

Max Act: 0.7247. Min Act: -0.0001

Data Index: 1094604 (C4 (Web Text))

Max Activating Token Index: 753

Text #6

Max Range: 0.8855. Min Range: -0.8855

Max Act: 0.7762. Min Act: -0.0001

Data Index: 1106634 (C4 (Web Text))

Max Activating Token Index: 220

Text #7

Max Range: 0.8855. Min Range: -0.8855

Max Act: 0.7498. Min Act: -0.0001

Data Index: 728519 (C4 (Web Text))

Max Activating Token Index: 701

Text #8

Max Range: 0.8855. Min Range: -0.8855

Max Act: 0.7970. Min Act: -0.0001

Data Index: 929253 (C4 (Web Text))

Max Activating Token Index: 262

Text #9

Max Range: 0.8855. Min Range: -0.8855

Max Act: 0.7837. Min Act: -0.0001

Data Index: 1059047 (C4 (Web Text))

Max Activating Token Index: 281

Text #10

Max Range: 0.8855. Min Range: -0.8855

Max Act: 0.7237. Min Act: -0.0001

Data Index: 1154173 (C4 (Web Text))

Max Activating Token Index: 698

Text #11

Max Range: 0.8855. Min Range: -0.8855

Max Act: 0.6964. Min Act: -0.0001

Data Index: 974640 (C4 (Web Text))

Max Activating Token Index: 191

Text #12

Max Range: 0.8855. Min Range: -0.8855

Max Act: 0.7256. Min Act: -0.0001

Data Index: 249741 (C4 (Web Text))

Max Activating Token Index: 960

Text #13

Max Range: 0.8855. Min Range: -0.8855

Max Act: 0.7288. Min Act: -0.0001

Data Index: 774670 (C4 (Web Text))

Max Activating Token Index: 763

Text #14

Max Range: 0.8855. Min Range: -0.8855

Max Act: 0.7685. Min Act: -0.0001

Data Index: 455212 (C4 (Web Text))

Max Activating Token Index: 306

Text #15

Max Range: 0.8855. Min Range: -0.8855

Max Act: 0.7225. Min Act: -0.0001

Data Index: 738151 (C4 (Web Text))

Max Activating Token Index: 375

Text #16

Max Range: 0.8855. Min Range: -0.8855

Max Act: 0.6771. Min Act: -0.0001

Data Index: 1013404 (C4 (Web Text))

Max Activating Token Index: 392

Text #17

Max Range: 0.8855. Min Range: -0.8855

Max Act: 0.7226. Min Act: -0.0001

Data Index: 936371 (C4 (Web Text))

Max Activating Token Index: 628

Text #18

Max Range: 0.8855. Min Range: -0.8855

Max Act: 0.6956. Min Act: -0.0001

Data Index: 102223 (C4 (Web Text))

Max Activating Token Index: 357

Text #19

Max Range: 0.8855. Min Range: -0.8855

Max Act: 0.7035. Min Act: -0.0001

Data Index: 1072965 (C4 (Web Text))

Max Activating Token Index: 918