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

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

Neuron 3348 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7375. Min Range: -0.7375

Max Act: 0.7166. Min Act: -0.0002

Data Index: 480110 (C4 (Web Text))

Max Activating Token Index: 771

Text #1

Max Range: 0.7375. Min Range: -0.7375

Max Act: 0.7375. Min Act: -0.0002

Data Index: 92630 (C4 (Web Text))

Max Activating Token Index: 621

Text #2

Max Range: 0.7375. Min Range: -0.7375

Max Act: 0.6632. Min Act: -0.0002

Data Index: 9605 (C4 (Web Text))

Max Activating Token Index: 435

Text #3

Max Range: 0.7375. Min Range: -0.7375

Max Act: 0.6968. Min Act: -0.0002

Data Index: 381757 (C4 (Web Text))

Max Activating Token Index: 27

Text #4

Max Range: 0.7375. Min Range: -0.7375

Max Act: 0.6374. Min Act: -0.0002

Data Index: 437480 (C4 (Web Text))

Max Activating Token Index: 698

Text #5

Max Range: 0.7375. Min Range: -0.7375

Max Act: 0.6816. Min Act: -0.0002

Data Index: 450416 (C4 (Web Text))

Max Activating Token Index: 579

Text #6

Max Range: 0.7375. Min Range: -0.7375

Max Act: 0.6317. Min Act: -0.0002

Data Index: 41970 (C4 (Web Text))

Max Activating Token Index: 21

Text #7

Max Range: 0.7375. Min Range: -0.7375

Max Act: 0.6582. Min Act: -0.0002

Data Index: 875451 (C4 (Web Text))

Max Activating Token Index: 125

Text #8

Max Range: 0.7375. Min Range: -0.7375

Max Act: 0.6619. Min Act: -0.0002

Data Index: 619869 (C4 (Web Text))

Max Activating Token Index: 224

Text #9

Max Range: 0.7375. Min Range: -0.7375

Max Act: 0.6390. Min Act: -0.0002

Data Index: 162757 (C4 (Web Text))

Max Activating Token Index: 822

Text #10

Max Range: 0.7375. Min Range: -0.7375

Max Act: 0.6723. Min Act: -0.0002

Data Index: 1114504 (C4 (Web Text))

Max Activating Token Index: 264

Text #11

Max Range: 0.7375. Min Range: -0.7375

Max Act: 0.6311. Min Act: -0.0002

Data Index: 1337979 (C4 (Web Text))

Max Activating Token Index: 880

Text #12

Max Range: 0.7375. Min Range: -0.7375

Max Act: 0.6273. Min Act: -0.0002

Data Index: 229450 (C4 (Web Text))

Max Activating Token Index: 670

Text #13

Max Range: 0.7375. Min Range: -0.7375

Max Act: 0.6089. Min Act: -0.0002

Data Index: 555778 (C4 (Web Text))

Max Activating Token Index: 191

Text #14

Max Range: 0.7375. Min Range: -0.7375

Max Act: 0.7209. Min Act: -0.0002

Data Index: 530504 (C4 (Web Text))

Max Activating Token Index: 635

Text #15

Max Range: 0.7375. Min Range: -0.7375

Max Act: 0.6040. Min Act: -0.0002

Data Index: 1141622 (C4 (Web Text))

Max Activating Token Index: 307

Text #16

Max Range: 0.7375. Min Range: -0.7375

Max Act: 0.5946. Min Act: -0.0002

Data Index: 1323952 (C4 (Web Text))

Max Activating Token Index: 489

Text #17

Max Range: 0.7375. Min Range: -0.7375

Max Act: 0.5490. Min Act: -0.0002

Data Index: 1136735 (C4 (Web Text))

Max Activating Token Index: 876

Text #18

Max Range: 0.7375. Min Range: -0.7375

Max Act: 0.6070. Min Act: -0.0002

Data Index: 33346 (C4 (Web Text))

Max Activating Token Index: 9

Text #19

Max Range: 0.7375. Min Range: -0.7375

Max Act: 0.6098. Min Act: -0.0002

Data Index: 593146 (C4 (Web Text))

Max Activating Token Index: 546