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

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

Neuron 4612 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7721. Min Range: -0.7721

Max Act: 0.7492. Min Act: -0.0000

Data Index: 940757 (C4 (Web Text))

Max Activating Token Index: 343

Text #1

Max Range: 0.7721. Min Range: -0.7721

Max Act: 0.7721. Min Act: -0.0000

Data Index: 1351767 (C4 (Web Text))

Max Activating Token Index: 902

Text #2

Max Range: 0.7721. Min Range: -0.7721

Max Act: 0.6231. Min Act: -0.0000

Data Index: 1217542 (C4 (Web Text))

Max Activating Token Index: 121

Text #3

Max Range: 0.7721. Min Range: -0.7721

Max Act: 0.5810. Min Act: -0.0000

Data Index: 518290 (C4 (Web Text))

Max Activating Token Index: 508

Text #4

Max Range: 0.7721. Min Range: -0.7721

Max Act: 0.6214. Min Act: -0.0000

Data Index: 1264810 (C4 (Web Text))

Max Activating Token Index: 418

Text #5

Max Range: 0.7721. Min Range: -0.7721

Max Act: 0.5905. Min Act: -0.0000

Data Index: 162654 (C4 (Web Text))

Max Activating Token Index: 60

Text #6

Max Range: 0.7721. Min Range: -0.7721

Max Act: 0.5592. Min Act: -0.0000

Data Index: 995055 (C4 (Web Text))

Max Activating Token Index: 344

Text #7

Max Range: 0.7721. Min Range: -0.7721

Max Act: 0.5774. Min Act: -0.0000

Data Index: 329230 (C4 (Web Text))

Max Activating Token Index: 966

Text #8

Max Range: 0.7721. Min Range: -0.7721

Max Act: 0.5748. Min Act: -0.0000

Data Index: 274850 (C4 (Web Text))

Max Activating Token Index: 307

Text #9

Max Range: 0.7721. Min Range: -0.7721

Max Act: 0.5712. Min Act: -0.0000

Data Index: 850902 (C4 (Web Text))

Max Activating Token Index: 641

Text #10

Max Range: 0.7721. Min Range: -0.7721

Max Act: 0.5725. Min Act: -0.0000

Data Index: 346581 (C4 (Web Text))

Max Activating Token Index: 393

Text #11

Max Range: 0.7721. Min Range: -0.7721

Max Act: 0.5353. Min Act: -0.0000

Data Index: 1297157 (C4 (Web Text))

Max Activating Token Index: 1000

Text #12

Max Range: 0.7721. Min Range: -0.7721

Max Act: 0.5249. Min Act: -0.0000

Data Index: 790112 (C4 (Web Text))

Max Activating Token Index: 698

Text #13

Max Range: 0.7721. Min Range: -0.7721

Max Act: 0.5031. Min Act: -0.0000

Data Index: 500462 (C4 (Web Text))

Max Activating Token Index: 192

Text #14

Max Range: 0.7721. Min Range: -0.7721

Max Act: 0.5280. Min Act: -0.0000

Data Index: 879296 (C4 (Web Text))

Max Activating Token Index: 640

Text #15

Max Range: 0.7721. Min Range: -0.7721

Max Act: 0.4517. Min Act: -0.0000

Data Index: 692355 (C4 (Web Text))

Max Activating Token Index: 980

Text #16

Max Range: 0.7721. Min Range: -0.7721

Max Act: 0.4638. Min Act: -0.0000

Data Index: 1326473 (C4 (Web Text))

Max Activating Token Index: 256

Text #17

Max Range: 0.7721. Min Range: -0.7721

Max Act: 0.4414. Min Act: -0.0000

Data Index: 1178414 (C4 (Web Text))

Max Activating Token Index: 130

Text #18

Max Range: 0.7721. Min Range: -0.7721

Max Act: 0.4507. Min Act: -0.0000

Data Index: 518806 (C4 (Web Text))

Max Activating Token Index: 974

Text #19

Max Range: 0.7721. Min Range: -0.7721

Max Act: 0.4865. Min Act: -0.0000

Data Index: 1243141 (C4 (Web Text))

Max Activating Token Index: 498