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

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

Neuron 1300 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7023. Min Range: -0.7023

Max Act: 0.7023. Min Act: -0.0000

Data Index: 450281 (C4 (Web Text))

Max Activating Token Index: 316

Text #1

Max Range: 0.7023. Min Range: -0.7023

Max Act: 0.6996. Min Act: -0.0000

Data Index: 831511 (C4 (Web Text))

Max Activating Token Index: 508

Text #2

Max Range: 0.7023. Min Range: -0.7023

Max Act: 0.6030. Min Act: -0.0000

Data Index: 117090 (C4 (Web Text))

Max Activating Token Index: 781

Text #3

Max Range: 0.7023. Min Range: -0.7023

Max Act: 0.6338. Min Act: -0.0000

Data Index: 712712 (C4 (Web Text))

Max Activating Token Index: 382

Text #4

Max Range: 0.7023. Min Range: -0.7023

Max Act: 0.5572. Min Act: -0.0000

Data Index: 700406 (C4 (Web Text))

Max Activating Token Index: 264

Text #5

Max Range: 0.7023. Min Range: -0.7023

Max Act: 0.4656. Min Act: 0.0000

Data Index: 201672 (C4 (Web Text))

Max Activating Token Index: 962

Text #6

Max Range: 0.7023. Min Range: -0.7023

Max Act: 0.4879. Min Act: -0.0000

Data Index: 1086636 (C4 (Web Text))

Max Activating Token Index: 400

Text #7

Max Range: 0.7023. Min Range: -0.7023

Max Act: 0.4588. Min Act: 0.0000

Data Index: 914983 (C4 (Web Text))

Max Activating Token Index: 278

Text #8

Max Range: 0.7023. Min Range: -0.7023

Max Act: 0.4426. Min Act: -0.0000

Data Index: 298648 (C4 (Web Text))

Max Activating Token Index: 340

Text #9

Max Range: 0.7023. Min Range: -0.7023

Max Act: 0.4452. Min Act: -0.0000

Data Index: 880932 (C4 (Web Text))

Max Activating Token Index: 171

Text #10

Max Range: 0.7023. Min Range: -0.7023

Max Act: 0.4367. Min Act: -0.0000

Data Index: 1186753 (C4 (Web Text))

Max Activating Token Index: 533

Text #11

Max Range: 0.7023. Min Range: -0.7023

Max Act: 0.4481. Min Act: -0.0000

Data Index: 319810 (C4 (Web Text))

Max Activating Token Index: 320

Text #12

Max Range: 0.7023. Min Range: -0.7023

Max Act: 0.4279. Min Act: -0.0000

Data Index: 638840 (C4 (Web Text))

Max Activating Token Index: 503

Text #13

Max Range: 0.7023. Min Range: -0.7023

Max Act: 0.4383. Min Act: -0.0000

Data Index: 323378 (C4 (Web Text))

Max Activating Token Index: 196

Text #14

Max Range: 0.7023. Min Range: -0.7023

Max Act: 0.3477. Min Act: -0.0000

Data Index: 878988 (C4 (Web Text))

Max Activating Token Index: 138

Text #15

Max Range: 0.7023. Min Range: -0.7023

Max Act: 0.3992. Min Act: -0.0000

Data Index: 858861 (C4 (Web Text))

Max Activating Token Index: 960

Text #16

Max Range: 0.7023. Min Range: -0.7023

Max Act: 0.4027. Min Act: 0.0000

Data Index: 347899 (C4 (Web Text))

Max Activating Token Index: 510

Text #17

Max Range: 0.7023. Min Range: -0.7023

Max Act: 0.4352. Min Act: -0.0000

Data Index: 1134211 (C4 (Web Text))

Max Activating Token Index: 717

Text #18

Max Range: 0.7023. Min Range: -0.7023

Max Act: 0.4142. Min Act: -0.0000

Data Index: 60607 (C4 (Web Text))

Max Activating Token Index: 705

Text #19

Max Range: 0.7023. Min Range: -0.7023

Max Act: 0.4006. Min Act: -0.0000

Data Index: 51075 (C4 (Web Text))

Max Activating Token Index: 105