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

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

Neuron 2106 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: 1.3383. Min Range: -1.3383

Max Act: 1.3383. Min Act: -0.0000

Data Index: 1640812 (Python Code)

Max Activating Token Index: 924

Text #1

Max Range: 1.3383. Min Range: -1.3383

Max Act: 1.2724. Min Act: -0.0000

Data Index: 421541 (C4 (Web Text))

Max Activating Token Index: 85

Text #2

Max Range: 1.3383. Min Range: -1.3383

Max Act: 1.0160. Min Act: -0.0000

Data Index: 991110 (C4 (Web Text))

Max Activating Token Index: 753

Text #3

Max Range: 1.3383. Min Range: -1.3383

Max Act: 1.0461. Min Act: -0.0000

Data Index: 855882 (C4 (Web Text))

Max Activating Token Index: 669

Text #4

Max Range: 1.3383. Min Range: -1.3383

Max Act: 1.1302. Min Act: -0.0000

Data Index: 856567 (C4 (Web Text))

Max Activating Token Index: 139

Text #5

Max Range: 1.3383. Min Range: -1.3383

Max Act: 1.1041. Min Act: -0.0000

Data Index: 1485662 (Python Code)

Max Activating Token Index: 903

Text #6

Max Range: 1.3383. Min Range: -1.3383

Max Act: 1.1291. Min Act: -0.0000

Data Index: 1643138 (Python Code)

Max Activating Token Index: 156

Text #7

Max Range: 1.3383. Min Range: -1.3383

Max Act: 1.0437. Min Act: -0.0000

Data Index: 577697 (C4 (Web Text))

Max Activating Token Index: 233

Text #8

Max Range: 1.3383. Min Range: -1.3383

Max Act: 0.9857. Min Act: -0.0001

Data Index: 76400 (C4 (Web Text))

Max Activating Token Index: 268

Text #9

Max Range: 1.3383. Min Range: -1.3383

Max Act: 1.0322. Min Act: -0.0000

Data Index: 1487765 (Python Code)

Max Activating Token Index: 587

Text #10

Max Range: 1.3383. Min Range: -1.3383

Max Act: 1.0127. Min Act: -0.0000

Data Index: 1617247 (Python Code)

Max Activating Token Index: 174

Text #11

Max Range: 1.3383. Min Range: -1.3383

Max Act: 1.0029. Min Act: -0.0000

Data Index: 1649129 (Python Code)

Max Activating Token Index: 476

Text #12

Max Range: 1.3383. Min Range: -1.3383

Max Act: 1.0222. Min Act: -0.0000

Data Index: 865835 (C4 (Web Text))

Max Activating Token Index: 178

Text #13

Max Range: 1.3383. Min Range: -1.3383

Max Act: 1.0379. Min Act: -0.0000

Data Index: 1192854 (C4 (Web Text))

Max Activating Token Index: 430

Text #14

Max Range: 1.3383. Min Range: -1.3383

Max Act: 0.9619. Min Act: -0.0000

Data Index: 1588255 (Python Code)

Max Activating Token Index: 526

Text #15

Max Range: 1.3383. Min Range: -1.3383

Max Act: 0.9886. Min Act: -0.0000

Data Index: 1547974 (Python Code)

Max Activating Token Index: 502

Text #16

Max Range: 1.3383. Min Range: -1.3383

Max Act: 0.9258. Min Act: -0.0000

Data Index: 573849 (C4 (Web Text))

Max Activating Token Index: 556

Text #17

Max Range: 1.3383. Min Range: -1.3383

Max Act: 0.9502. Min Act: -0.0000

Data Index: 1577484 (Python Code)

Max Activating Token Index: 744

Text #18

Max Range: 1.3383. Min Range: -1.3383

Max Act: 0.8573. Min Act: -0.0000

Data Index: 1515935 (Python Code)

Max Activating Token Index: 710

Text #19

Max Range: 1.3383. Min Range: -1.3383

Max Act: 0.9123. Min Act: -0.0000

Data Index: 318328 (C4 (Web Text))

Max Activating Token Index: 629