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

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

Neuron 383 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: 1.3065. Min Range: -1.3065

Max Act: 1.3065. Min Act: -0.0000

Data Index: 127087 (C4 (Web Text))

Max Activating Token Index: 143

Text #1

Max Range: 1.3065. Min Range: -1.3065

Max Act: 1.2694. Min Act: -0.0000

Data Index: 1320093 (C4 (Web Text))

Max Activating Token Index: 275

Text #2

Max Range: 1.3065. Min Range: -1.3065

Max Act: 1.1733. Min Act: -0.0000

Data Index: 527881 (C4 (Web Text))

Max Activating Token Index: 204

Text #3

Max Range: 1.3065. Min Range: -1.3065

Max Act: 1.1968. Min Act: -0.0000

Data Index: 1132478 (C4 (Web Text))

Max Activating Token Index: 107

Text #4

Max Range: 1.3065. Min Range: -1.3065

Max Act: 1.1780. Min Act: -0.0000

Data Index: 1053722 (C4 (Web Text))

Max Activating Token Index: 917

Text #5

Max Range: 1.3065. Min Range: -1.3065

Max Act: 1.2048. Min Act: -0.0000

Data Index: 375570 (C4 (Web Text))

Max Activating Token Index: 414

Text #6

Max Range: 1.3065. Min Range: -1.3065

Max Act: 1.0574. Min Act: -0.0000

Data Index: 1354572 (C4 (Web Text))

Max Activating Token Index: 623

Text #7

Max Range: 1.3065. Min Range: -1.3065

Max Act: 1.1204. Min Act: -0.0000

Data Index: 277502 (C4 (Web Text))

Max Activating Token Index: 209

Text #8

Max Range: 1.3065. Min Range: -1.3065

Max Act: 1.1400. Min Act: -0.0000

Data Index: 518742 (C4 (Web Text))

Max Activating Token Index: 676

Text #9

Max Range: 1.3065. Min Range: -1.3065

Max Act: 1.1582. Min Act: -0.0000

Data Index: 779188 (C4 (Web Text))

Max Activating Token Index: 942

Text #10

Max Range: 1.3065. Min Range: -1.3065

Max Act: 1.1166. Min Act: -0.0000

Data Index: 180942 (C4 (Web Text))

Max Activating Token Index: 495

Text #11

Max Range: 1.3065. Min Range: -1.3065

Max Act: 1.0610. Min Act: -0.0000

Data Index: 71668 (C4 (Web Text))

Max Activating Token Index: 488

Text #12

Max Range: 1.3065. Min Range: -1.3065

Max Act: 1.0611. Min Act: -0.0000

Data Index: 329793 (C4 (Web Text))

Max Activating Token Index: 895

Text #13

Max Range: 1.3065. Min Range: -1.3065

Max Act: 1.0740. Min Act: -0.0000

Data Index: 1167669 (C4 (Web Text))

Max Activating Token Index: 505

Text #14

Max Range: 1.3065. Min Range: -1.3065

Max Act: 1.0694. Min Act: -0.0000

Data Index: 37088 (C4 (Web Text))

Max Activating Token Index: 84

Text #15

Max Range: 1.3065. Min Range: -1.3065

Max Act: 1.0397. Min Act: -0.0000

Data Index: 1131413 (C4 (Web Text))

Max Activating Token Index: 293

Text #16

Max Range: 1.3065. Min Range: -1.3065

Max Act: 1.0235. Min Act: -0.0000

Data Index: 1264590 (C4 (Web Text))

Max Activating Token Index: 184

Text #17

Max Range: 1.3065. Min Range: -1.3065

Max Act: 1.0487. Min Act: -0.0000

Data Index: 785207 (C4 (Web Text))

Max Activating Token Index: 55

Text #18

Max Range: 1.3065. Min Range: -1.3065

Max Act: 1.0525. Min Act: -0.0000

Data Index: 349660 (C4 (Web Text))

Max Activating Token Index: 37

Text #19

Max Range: 1.3065. Min Range: -1.3065

Max Act: 1.0668. Min Act: -0.0000

Data Index: 685825 (C4 (Web Text))

Max Activating Token Index: 618