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

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

Neuron 2721 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: 0.7264. Min Range: -0.7264

Max Act: 0.7264. Min Act: -0.0000

Data Index: 547369 (C4 (Web Text))

Max Activating Token Index: 257

Text #1

Max Range: 0.7264. Min Range: -0.7264

Max Act: 0.6175. Min Act: -0.0000

Data Index: 1058621 (C4 (Web Text))

Max Activating Token Index: 996

Text #2

Max Range: 0.7264. Min Range: -0.7264

Max Act: 0.5372. Min Act: -0.0000

Data Index: 473957 (C4 (Web Text))

Max Activating Token Index: 669

Text #3

Max Range: 0.7264. Min Range: -0.7264

Max Act: 0.5000. Min Act: -0.0000

Data Index: 1358515 (C4 (Web Text))

Max Activating Token Index: 673

Text #4

Max Range: 0.7264. Min Range: -0.7264

Max Act: 0.4711. Min Act: -0.0000

Data Index: 242876 (C4 (Web Text))

Max Activating Token Index: 825

Text #5

Max Range: 0.7264. Min Range: -0.7264

Max Act: 0.5106. Min Act: -0.0000

Data Index: 1515373 (Python Code)

Max Activating Token Index: 909

Text #6

Max Range: 0.7264. Min Range: -0.7264

Max Act: 0.4915. Min Act: -0.0000

Data Index: 690285 (C4 (Web Text))

Max Activating Token Index: 885

Text #7

Max Range: 0.7264. Min Range: -0.7264

Max Act: 0.5027. Min Act: -0.0000

Data Index: 1073019 (C4 (Web Text))

Max Activating Token Index: 329

Text #8

Max Range: 0.7264. Min Range: -0.7264

Max Act: 0.4973. Min Act: -0.0000

Data Index: 471563 (C4 (Web Text))

Max Activating Token Index: 420

Text #9

Max Range: 0.7264. Min Range: -0.7264

Max Act: 0.4699. Min Act: -0.0000

Data Index: 257450 (C4 (Web Text))

Max Activating Token Index: 380

Text #10

Max Range: 0.7264. Min Range: -0.7264

Max Act: 0.4756. Min Act: -0.0000

Data Index: 352613 (C4 (Web Text))

Max Activating Token Index: 875

Text #11

Max Range: 0.7264. Min Range: -0.7264

Max Act: 0.4527. Min Act: -0.0000

Data Index: 809049 (C4 (Web Text))

Max Activating Token Index: 249

Text #12

Max Range: 0.7264. Min Range: -0.7264

Max Act: 0.4490. Min Act: -0.0000

Data Index: 774731 (C4 (Web Text))

Max Activating Token Index: 61

Text #13

Max Range: 0.7264. Min Range: -0.7264

Max Act: 0.4629. Min Act: -0.0000

Data Index: 807205 (C4 (Web Text))

Max Activating Token Index: 192

Text #14

Max Range: 0.7264. Min Range: -0.7264

Max Act: 0.4715. Min Act: -0.0000

Data Index: 1250364 (C4 (Web Text))

Max Activating Token Index: 422

Text #15

Max Range: 0.7264. Min Range: -0.7264

Max Act: 0.4534. Min Act: -0.0000

Data Index: 1091307 (C4 (Web Text))

Max Activating Token Index: 929

Text #16

Max Range: 0.7264. Min Range: -0.7264

Max Act: 0.4884. Min Act: -0.0000

Data Index: 1344994 (C4 (Web Text))

Max Activating Token Index: 812

Text #17

Max Range: 0.7264. Min Range: -0.7264

Max Act: 0.4352. Min Act: -0.0000

Data Index: 132064 (C4 (Web Text))

Max Activating Token Index: 978

Text #18

Max Range: 0.7264. Min Range: -0.7264

Max Act: 0.4418. Min Act: -0.0000

Data Index: 1176344 (C4 (Web Text))

Max Activating Token Index: 194

Text #19

Max Range: 0.7264. Min Range: -0.7264

Max Act: 0.3964. Min Act: -0.0000

Data Index: 1184350 (C4 (Web Text))

Max Activating Token Index: 294