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

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

Neuron 4203 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: 0.8508. Min Range: -0.8508

Max Act: 0.8508. Min Act: -0.0000

Data Index: 918172 (C4 (Web Text))

Max Activating Token Index: 71

Text #1

Max Range: 0.8508. Min Range: -0.8508

Max Act: 0.6581. Min Act: -0.0000

Data Index: 1186447 (C4 (Web Text))

Max Activating Token Index: 239

Text #2

Max Range: 0.8508. Min Range: -0.8508

Max Act: 0.5638. Min Act: -0.0000

Data Index: 1177460 (C4 (Web Text))

Max Activating Token Index: 120

Text #3

Max Range: 0.8508. Min Range: -0.8508

Max Act: 0.4792. Min Act: -0.0000

Data Index: 253030 (C4 (Web Text))

Max Activating Token Index: 173

Text #4

Max Range: 0.8508. Min Range: -0.8508

Max Act: 0.5111. Min Act: -0.0000

Data Index: 437502 (C4 (Web Text))

Max Activating Token Index: 594

Text #5

Max Range: 0.8508. Min Range: -0.8508

Max Act: 0.4730. Min Act: -0.0000

Data Index: 1292997 (C4 (Web Text))

Max Activating Token Index: 866

Text #6

Max Range: 0.8508. Min Range: -0.8508

Max Act: 0.4674. Min Act: -0.0000

Data Index: 963391 (C4 (Web Text))

Max Activating Token Index: 966

Text #7

Max Range: 0.8508. Min Range: -0.8508

Max Act: 0.4780. Min Act: -0.0000

Data Index: 905508 (C4 (Web Text))

Max Activating Token Index: 42

Text #8

Max Range: 0.8508. Min Range: -0.8508

Max Act: 0.4583. Min Act: -0.0000

Data Index: 144876 (C4 (Web Text))

Max Activating Token Index: 425

Text #9

Max Range: 0.8508. Min Range: -0.8508

Max Act: 0.4717. Min Act: -0.0000

Data Index: 186554 (C4 (Web Text))

Max Activating Token Index: 1015

Text #10

Max Range: 0.8508. Min Range: -0.8508

Max Act: 0.4443. Min Act: -0.0000

Data Index: 426297 (C4 (Web Text))

Max Activating Token Index: 635

Text #11

Max Range: 0.8508. Min Range: -0.8508

Max Act: 0.4279. Min Act: -0.0000

Data Index: 1271529 (C4 (Web Text))

Max Activating Token Index: 123

Text #12

Max Range: 0.8508. Min Range: -0.8508

Max Act: 0.4418. Min Act: -0.0000

Data Index: 721790 (C4 (Web Text))

Max Activating Token Index: 637

Text #13

Max Range: 0.8508. Min Range: -0.8508

Max Act: 0.4235. Min Act: -0.0000

Data Index: 738762 (C4 (Web Text))

Max Activating Token Index: 741

Text #14

Max Range: 0.8508. Min Range: -0.8508

Max Act: 0.4274. Min Act: -0.0000

Data Index: 517003 (C4 (Web Text))

Max Activating Token Index: 878

Text #15

Max Range: 0.8508. Min Range: -0.8508

Max Act: 0.4178. Min Act: -0.0000

Data Index: 12185 (C4 (Web Text))

Max Activating Token Index: 517

Text #16

Max Range: 0.8508. Min Range: -0.8508

Max Act: 0.4028. Min Act: -0.0000

Data Index: 130324 (C4 (Web Text))

Max Activating Token Index: 898

Text #17

Max Range: 0.8508. Min Range: -0.8508

Max Act: 0.4056. Min Act: -0.0000

Data Index: 1274145 (C4 (Web Text))

Max Activating Token Index: 411

Text #18

Max Range: 0.8508. Min Range: -0.8508

Max Act: 0.3905. Min Act: -0.0000

Data Index: 388334 (C4 (Web Text))

Max Activating Token Index: 136

Text #19

Max Range: 0.8508. Min Range: -0.8508

Max Act: 0.3906. Min Act: -0.0000

Data Index: 1101226 (C4 (Web Text))

Max Activating Token Index: 160