Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 851 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.7343. Min Range: -0.7343

Max Act: 0.7343. Min Act: -0.0000

Data Index: 1119885 (C4 (Web Text))

Max Activating Token Index: 879

Text #1

Max Range: 0.7343. Min Range: -0.7343

Max Act: 0.6301. Min Act: -0.0000

Data Index: 808765 (C4 (Web Text))

Max Activating Token Index: 784

Text #2

Max Range: 0.7343. Min Range: -0.7343

Max Act: 0.5380. Min Act: -0.0000

Data Index: 724097 (C4 (Web Text))

Max Activating Token Index: 308

Text #3

Max Range: 0.7343. Min Range: -0.7343

Max Act: 0.5425. Min Act: -0.0000

Data Index: 736328 (C4 (Web Text))

Max Activating Token Index: 700

Text #4

Max Range: 0.7343. Min Range: -0.7343

Max Act: 0.5161. Min Act: -0.0000

Data Index: 327132 (C4 (Web Text))

Max Activating Token Index: 379

Text #5

Max Range: 0.7343. Min Range: -0.7343

Max Act: 0.5124. Min Act: -0.0000

Data Index: 1057206 (C4 (Web Text))

Max Activating Token Index: 798

Text #6

Max Range: 0.7343. Min Range: -0.7343

Max Act: 0.5231. Min Act: -0.0000

Data Index: 930419 (C4 (Web Text))

Max Activating Token Index: 310

Text #7

Max Range: 0.7343. Min Range: -0.7343

Max Act: 0.5195. Min Act: -0.0000

Data Index: 371281 (C4 (Web Text))

Max Activating Token Index: 551

Text #8

Max Range: 0.7343. Min Range: -0.7343

Max Act: 0.5014. Min Act: -0.0000

Data Index: 1045748 (C4 (Web Text))

Max Activating Token Index: 162

Text #9

Max Range: 0.7343. Min Range: -0.7343

Max Act: 0.4907. Min Act: -0.0000

Data Index: 820609 (C4 (Web Text))

Max Activating Token Index: 539

Text #10

Max Range: 0.7343. Min Range: -0.7343

Max Act: 0.5226. Min Act: -0.0000

Data Index: 481174 (C4 (Web Text))

Max Activating Token Index: 341

Text #11

Max Range: 0.7343. Min Range: -0.7343

Max Act: 0.4890. Min Act: -0.0000

Data Index: 925024 (C4 (Web Text))

Max Activating Token Index: 131

Text #12

Max Range: 0.7343. Min Range: -0.7343

Max Act: 0.4878. Min Act: -0.0000

Data Index: 54154 (C4 (Web Text))

Max Activating Token Index: 377

Text #13

Max Range: 0.7343. Min Range: -0.7343

Max Act: 0.4872. Min Act: -0.0000

Data Index: 986430 (C4 (Web Text))

Max Activating Token Index: 923

Text #14

Max Range: 0.7343. Min Range: -0.7343

Max Act: 0.4778. Min Act: -0.0000

Data Index: 131831 (C4 (Web Text))

Max Activating Token Index: 135

Text #15

Max Range: 0.7343. Min Range: -0.7343

Max Act: 0.5067. Min Act: -0.0000

Data Index: 274949 (C4 (Web Text))

Max Activating Token Index: 830

Text #16

Max Range: 0.7343. Min Range: -0.7343

Max Act: 0.4813. Min Act: -0.0000

Data Index: 884417 (C4 (Web Text))

Max Activating Token Index: 594

Text #17

Max Range: 0.7343. Min Range: -0.7343

Max Act: 0.4772. Min Act: -0.0000

Data Index: 1173165 (C4 (Web Text))

Max Activating Token Index: 950

Text #18

Max Range: 0.7343. Min Range: -0.7343

Max Act: 0.4538. Min Act: -0.0000

Data Index: 601247 (C4 (Web Text))

Max Activating Token Index: 534

Text #19

Max Range: 0.7343. Min Range: -0.7343

Max Act: 0.4537. Min Act: -0.0000

Data Index: 961525 (C4 (Web Text))

Max Activating Token Index: 222