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

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

Neuron 1129 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0301. Min Range: -1.0301

Max Act: 1.0301. Min Act: -0.0000

Data Index: 534154 (C4 (Web Text))

Max Activating Token Index: 677

Text #1

Max Range: 1.0301. Min Range: -1.0301

Max Act: 0.8079. Min Act: -0.0000

Data Index: 666828 (C4 (Web Text))

Max Activating Token Index: 992

Text #2

Max Range: 1.0301. Min Range: -1.0301

Max Act: 0.7950. Min Act: -0.0000

Data Index: 646506 (C4 (Web Text))

Max Activating Token Index: 226

Text #3

Max Range: 1.0301. Min Range: -1.0301

Max Act: 0.7753. Min Act: -0.0000

Data Index: 222573 (C4 (Web Text))

Max Activating Token Index: 68

Text #4

Max Range: 1.0301. Min Range: -1.0301

Max Act: 0.6756. Min Act: -0.0000

Data Index: 505000 (C4 (Web Text))

Max Activating Token Index: 838

Text #5

Max Range: 1.0301. Min Range: -1.0301

Max Act: 0.7147. Min Act: -0.0000

Data Index: 642010 (C4 (Web Text))

Max Activating Token Index: 466

Text #6

Max Range: 1.0301. Min Range: -1.0301

Max Act: 0.6452. Min Act: -0.0000

Data Index: 1025734 (C4 (Web Text))

Max Activating Token Index: 198

Text #7

Max Range: 1.0301. Min Range: -1.0301

Max Act: 0.6469. Min Act: -0.0000

Data Index: 162581 (C4 (Web Text))

Max Activating Token Index: 521

Text #8

Max Range: 1.0301. Min Range: -1.0301

Max Act: 0.7258. Min Act: -0.0000

Data Index: 273838 (C4 (Web Text))

Max Activating Token Index: 1006

Text #9

Max Range: 1.0301. Min Range: -1.0301

Max Act: 0.6903. Min Act: -0.0000

Data Index: 1218743 (C4 (Web Text))

Max Activating Token Index: 769

Text #10

Max Range: 1.0301. Min Range: -1.0301

Max Act: 0.6744. Min Act: -0.0000

Data Index: 1066930 (C4 (Web Text))

Max Activating Token Index: 151

Text #11

Max Range: 1.0301. Min Range: -1.0301

Max Act: 0.6930. Min Act: -0.0000

Data Index: 419544 (C4 (Web Text))

Max Activating Token Index: 408

Text #12

Max Range: 1.0301. Min Range: -1.0301

Max Act: 0.6669. Min Act: -0.0000

Data Index: 142370 (C4 (Web Text))

Max Activating Token Index: 703

Text #13

Max Range: 1.0301. Min Range: -1.0301

Max Act: 0.6847. Min Act: -0.0000

Data Index: 275433 (C4 (Web Text))

Max Activating Token Index: 733

Text #14

Max Range: 1.0301. Min Range: -1.0301

Max Act: 0.6324. Min Act: -0.0000

Data Index: 291270 (C4 (Web Text))

Max Activating Token Index: 462

Text #15

Max Range: 1.0301. Min Range: -1.0301

Max Act: 0.6279. Min Act: -0.0000

Data Index: 1146731 (C4 (Web Text))

Max Activating Token Index: 189

Text #16

Max Range: 1.0301. Min Range: -1.0301

Max Act: 0.6391. Min Act: -0.0000

Data Index: 1132491 (C4 (Web Text))

Max Activating Token Index: 7

Text #17

Max Range: 1.0301. Min Range: -1.0301

Max Act: 0.6149. Min Act: -0.0000

Data Index: 1194374 (C4 (Web Text))

Max Activating Token Index: 321

Text #18

Max Range: 1.0301. Min Range: -1.0301

Max Act: 0.6437. Min Act: -0.0000

Data Index: 523738 (C4 (Web Text))

Max Activating Token Index: 96

Text #19

Max Range: 1.0301. Min Range: -1.0301

Max Act: 0.6075. Min Act: -0.0000

Data Index: 226596 (C4 (Web Text))

Max Activating Token Index: 472