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

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

Neuron 1753 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7640. Min Range: -0.7640

Max Act: 0.7087. Min Act: -0.0000

Data Index: 721613 (C4 (Web Text))

Max Activating Token Index: 725

Text #1

Max Range: 0.7640. Min Range: -0.7640

Max Act: 0.7456. Min Act: -0.0000

Data Index: 234099 (C4 (Web Text))

Max Activating Token Index: 130

Text #2

Max Range: 0.7640. Min Range: -0.7640

Max Act: 0.7480. Min Act: -0.0000

Data Index: 542492 (C4 (Web Text))

Max Activating Token Index: 905

Text #3

Max Range: 0.7640. Min Range: -0.7640

Max Act: 0.7317. Min Act: -0.0000

Data Index: 1350810 (C4 (Web Text))

Max Activating Token Index: 421

Text #4

Max Range: 0.7640. Min Range: -0.7640

Max Act: 0.7640. Min Act: -0.0000

Data Index: 907269 (C4 (Web Text))

Max Activating Token Index: 188

Text #5

Max Range: 0.7640. Min Range: -0.7640

Max Act: 0.7390. Min Act: -0.0000

Data Index: 969236 (C4 (Web Text))

Max Activating Token Index: 775

Text #6

Max Range: 0.7640. Min Range: -0.7640

Max Act: 0.7463. Min Act: -0.0000

Data Index: 1308198 (C4 (Web Text))

Max Activating Token Index: 752

Text #7

Max Range: 0.7640. Min Range: -0.7640

Max Act: 0.6513. Min Act: -0.0000

Data Index: 1344294 (C4 (Web Text))

Max Activating Token Index: 927

Text #8

Max Range: 0.7640. Min Range: -0.7640

Max Act: 0.6717. Min Act: -0.0000

Data Index: 600271 (C4 (Web Text))

Max Activating Token Index: 854

Text #9

Max Range: 0.7640. Min Range: -0.7640

Max Act: 0.6275. Min Act: -0.0000

Data Index: 450857 (C4 (Web Text))

Max Activating Token Index: 258

Text #10

Max Range: 0.7640. Min Range: -0.7640

Max Act: 0.6647. Min Act: -0.0000

Data Index: 1265304 (C4 (Web Text))

Max Activating Token Index: 722

Text #11

Max Range: 0.7640. Min Range: -0.7640

Max Act: 0.6996. Min Act: -0.0000

Data Index: 756926 (C4 (Web Text))

Max Activating Token Index: 608

Text #12

Max Range: 0.7640. Min Range: -0.7640

Max Act: 0.6946. Min Act: -0.0000

Data Index: 1342644 (C4 (Web Text))

Max Activating Token Index: 135

Text #13

Max Range: 0.7640. Min Range: -0.7640

Max Act: 0.6730. Min Act: -0.0000

Data Index: 794959 (C4 (Web Text))

Max Activating Token Index: 680

Text #14

Max Range: 0.7640. Min Range: -0.7640

Max Act: 0.6432. Min Act: -0.0000

Data Index: 1219616 (C4 (Web Text))

Max Activating Token Index: 1021

Text #15

Max Range: 0.7640. Min Range: -0.7640

Max Act: 0.6687. Min Act: -0.0000

Data Index: 828659 (C4 (Web Text))

Max Activating Token Index: 250

Text #16

Max Range: 0.7640. Min Range: -0.7640

Max Act: 0.7196. Min Act: -0.0000

Data Index: 1186609 (C4 (Web Text))

Max Activating Token Index: 690

Text #17

Max Range: 0.7640. Min Range: -0.7640

Max Act: 0.6683. Min Act: -0.0000

Data Index: 806738 (C4 (Web Text))

Max Activating Token Index: 1000

Text #18

Max Range: 0.7640. Min Range: -0.7640

Max Act: 0.6422. Min Act: -0.0000

Data Index: 534088 (C4 (Web Text))

Max Activating Token Index: 14

Text #19

Max Range: 0.7640. Min Range: -0.7640

Max Act: 0.6659. Min Act: -0.0000

Data Index: 1074133 (C4 (Web Text))

Max Activating Token Index: 660