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

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

Neuron 870 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7613. Min Range: -0.7613

Max Act: 0.7166. Min Act: -0.0001

Data Index: 1224976 (C4 (Web Text))

Max Activating Token Index: 207

Text #1

Max Range: 0.7613. Min Range: -0.7613

Max Act: 0.5702. Min Act: -0.0001

Data Index: 867670 (C4 (Web Text))

Max Activating Token Index: 293

Text #2

Max Range: 0.7613. Min Range: -0.7613

Max Act: 0.4790. Min Act: -0.0001

Data Index: 33576 (C4 (Web Text))

Max Activating Token Index: 229

Text #3

Max Range: 0.7613. Min Range: -0.7613

Max Act: 0.6514. Min Act: -0.0001

Data Index: 1238897 (C4 (Web Text))

Max Activating Token Index: 627

Text #4

Max Range: 0.7613. Min Range: -0.7613

Max Act: 0.6884. Min Act: -0.0001

Data Index: 300836 (C4 (Web Text))

Max Activating Token Index: 910

Text #5

Max Range: 0.7613. Min Range: -0.7613

Max Act: 0.6618. Min Act: -0.0001

Data Index: 645237 (C4 (Web Text))

Max Activating Token Index: 246

Text #6

Max Range: 0.7613. Min Range: -0.7613

Max Act: 0.5017. Min Act: -0.0001

Data Index: 1090972 (C4 (Web Text))

Max Activating Token Index: 243

Text #7

Max Range: 0.7613. Min Range: -0.7613

Max Act: 0.7613. Min Act: -0.0001

Data Index: 421579 (C4 (Web Text))

Max Activating Token Index: 409

Text #8

Max Range: 0.7613. Min Range: -0.7613

Max Act: 0.6572. Min Act: -0.0001

Data Index: 180354 (C4 (Web Text))

Max Activating Token Index: 153

Text #9

Max Range: 0.7613. Min Range: -0.7613

Max Act: 0.4530. Min Act: -0.0001

Data Index: 1307453 (C4 (Web Text))

Max Activating Token Index: 133

Text #10

Max Range: 0.7613. Min Range: -0.7613

Max Act: 0.6569. Min Act: -0.0001

Data Index: 792386 (C4 (Web Text))

Max Activating Token Index: 265

Text #11

Max Range: 0.7613. Min Range: -0.7613

Max Act: 0.6196. Min Act: -0.0001

Data Index: 549279 (C4 (Web Text))

Max Activating Token Index: 894

Text #12

Max Range: 0.7613. Min Range: -0.7613

Max Act: 0.6787. Min Act: -0.0001

Data Index: 1142268 (C4 (Web Text))

Max Activating Token Index: 748

Text #13

Max Range: 0.7613. Min Range: -0.7613

Max Act: 0.5762. Min Act: -0.0001

Data Index: 839887 (C4 (Web Text))

Max Activating Token Index: 466

Text #14

Max Range: 0.7613. Min Range: -0.7613

Max Act: 0.6060. Min Act: -0.0001

Data Index: 1038574 (C4 (Web Text))

Max Activating Token Index: 797

Text #15

Max Range: 0.7613. Min Range: -0.7613

Max Act: 0.4002. Min Act: -0.0001

Data Index: 1212963 (C4 (Web Text))

Max Activating Token Index: 982

Text #16

Max Range: 0.7613. Min Range: -0.7613

Max Act: 0.6044. Min Act: -0.0001

Data Index: 1167133 (C4 (Web Text))

Max Activating Token Index: 960

Text #17

Max Range: 0.7613. Min Range: -0.7613

Max Act: 0.4723. Min Act: -0.0001

Data Index: 219392 (C4 (Web Text))

Max Activating Token Index: 479

Text #18

Max Range: 0.7613. Min Range: -0.7613

Max Act: 0.4405. Min Act: -0.0001

Data Index: 1147626 (C4 (Web Text))

Max Activating Token Index: 794

Text #19

Max Range: 0.7613. Min Range: -0.7613

Max Act: 0.6507. Min Act: -0.0001

Data Index: 60020 (C4 (Web Text))

Max Activating Token Index: 221