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

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

Neuron 1728 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5310. Min Range: -1.5310

Max Act: 1.5310. Min Act: -0.0000

Data Index: 343395 (C4 (Web Text))

Max Activating Token Index: 25

Text #1

Max Range: 1.5310. Min Range: -1.5310

Max Act: 1.1912. Min Act: -0.0000

Data Index: 683733 (C4 (Web Text))

Max Activating Token Index: 1011

Text #2

Max Range: 1.5310. Min Range: -1.5310

Max Act: 1.2628. Min Act: -0.0000

Data Index: 319691 (C4 (Web Text))

Max Activating Token Index: 240

Text #3

Max Range: 1.5310. Min Range: -1.5310

Max Act: 1.1678. Min Act: -0.0000

Data Index: 905975 (C4 (Web Text))

Max Activating Token Index: 696

Text #4

Max Range: 1.5310. Min Range: -1.5310

Max Act: 1.3249. Min Act: -0.0001

Data Index: 1249821 (C4 (Web Text))

Max Activating Token Index: 245

Text #5

Max Range: 1.5310. Min Range: -1.5310

Max Act: 1.1282. Min Act: -0.0000

Data Index: 1037978 (C4 (Web Text))

Max Activating Token Index: 1016

Text #6

Max Range: 1.5310. Min Range: -1.5310

Max Act: 1.0752. Min Act: -0.0000

Data Index: 271394 (C4 (Web Text))

Max Activating Token Index: 256

Text #7

Max Range: 1.5310. Min Range: -1.5310

Max Act: 1.2274. Min Act: -0.0001

Data Index: 157077 (C4 (Web Text))

Max Activating Token Index: 787

Text #8

Max Range: 1.5310. Min Range: -1.5310

Max Act: 1.0148. Min Act: -0.0000

Data Index: 720803 (C4 (Web Text))

Max Activating Token Index: 14

Text #9

Max Range: 1.5310. Min Range: -1.5310

Max Act: 0.9427. Min Act: -0.0000

Data Index: 525980 (C4 (Web Text))

Max Activating Token Index: 217

Text #10

Max Range: 1.5310. Min Range: -1.5310

Max Act: 1.0133. Min Act: -0.0000

Data Index: 1326783 (C4 (Web Text))

Max Activating Token Index: 926

Text #11

Max Range: 1.5310. Min Range: -1.5310

Max Act: 0.9783. Min Act: -0.0001

Data Index: 1122672 (C4 (Web Text))

Max Activating Token Index: 446

Text #12

Max Range: 1.5310. Min Range: -1.5310

Max Act: 0.9618. Min Act: -0.0000

Data Index: 1168689 (C4 (Web Text))

Max Activating Token Index: 489

Text #13

Max Range: 1.5310. Min Range: -1.5310

Max Act: 0.9234. Min Act: -0.0000

Data Index: 1089369 (C4 (Web Text))

Max Activating Token Index: 780

Text #14

Max Range: 1.5310. Min Range: -1.5310

Max Act: 0.9015. Min Act: -0.0001

Data Index: 489546 (C4 (Web Text))

Max Activating Token Index: 663

Text #15

Max Range: 1.5310. Min Range: -1.5310

Max Act: 0.8741. Min Act: -0.0000

Data Index: 160939 (C4 (Web Text))

Max Activating Token Index: 37

Text #16

Max Range: 1.5310. Min Range: -1.5310

Max Act: 0.8060. Min Act: -0.0001

Data Index: 356684 (C4 (Web Text))

Max Activating Token Index: 317

Text #17

Max Range: 1.5310. Min Range: -1.5310

Max Act: 0.8557. Min Act: -0.0000

Data Index: 825777 (C4 (Web Text))

Max Activating Token Index: 874

Text #18

Max Range: 1.5310. Min Range: -1.5310

Max Act: 0.8869. Min Act: -0.0000

Data Index: 633683 (C4 (Web Text))

Max Activating Token Index: 538

Text #19

Max Range: 1.5310. Min Range: -1.5310

Max Act: 0.7955. Min Act: -0.0000

Data Index: 926978 (C4 (Web Text))

Max Activating Token Index: 603