Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1004 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.8422. Min Range: -1.8422

Max Act: 1.7689. Min Act: -0.0001

Data Index: 326104 (C4 (Web Text))

Max Activating Token Index: 401

Text #1

Max Range: 1.8422. Min Range: -1.8422

Max Act: 1.7606. Min Act: -0.0001

Data Index: 1066378 (C4 (Web Text))

Max Activating Token Index: 547

Text #2

Max Range: 1.8422. Min Range: -1.8422

Max Act: 1.7509. Min Act: -0.0001

Data Index: 239497 (C4 (Web Text))

Max Activating Token Index: 323

Text #3

Max Range: 1.8422. Min Range: -1.8422

Max Act: 1.8422. Min Act: -0.0001

Data Index: 171666 (C4 (Web Text))

Max Activating Token Index: 142

Text #4

Max Range: 1.8422. Min Range: -1.8422

Max Act: 1.6816. Min Act: -0.0001

Data Index: 576501 (C4 (Web Text))

Max Activating Token Index: 373

Text #5

Max Range: 1.8422. Min Range: -1.8422

Max Act: 1.6483. Min Act: -0.0001

Data Index: 365499 (C4 (Web Text))

Max Activating Token Index: 29

Text #6

Max Range: 1.8422. Min Range: -1.8422

Max Act: 1.4992. Min Act: -0.0001

Data Index: 940523 (C4 (Web Text))

Max Activating Token Index: 483

Text #7

Max Range: 1.8422. Min Range: -1.8422

Max Act: 1.5669. Min Act: -0.0001

Data Index: 1060944 (C4 (Web Text))

Max Activating Token Index: 99

Text #8

Max Range: 1.8422. Min Range: -1.8422

Max Act: 1.6614. Min Act: -0.0001

Data Index: 573033 (C4 (Web Text))

Max Activating Token Index: 324

Text #9

Max Range: 1.8422. Min Range: -1.8422

Max Act: 1.4916. Min Act: -0.0001

Data Index: 395696 (C4 (Web Text))

Max Activating Token Index: 293

Text #10

Max Range: 1.8422. Min Range: -1.8422

Max Act: 1.6370. Min Act: -0.0001

Data Index: 727538 (C4 (Web Text))

Max Activating Token Index: 569

Text #11

Max Range: 1.8422. Min Range: -1.8422

Max Act: 1.5219. Min Act: -0.0001

Data Index: 983969 (C4 (Web Text))

Max Activating Token Index: 121

Text #12

Max Range: 1.8422. Min Range: -1.8422

Max Act: 1.5982. Min Act: -0.0001

Data Index: 207737 (C4 (Web Text))

Max Activating Token Index: 673

Text #13

Max Range: 1.8422. Min Range: -1.8422

Max Act: 1.5344. Min Act: -0.0001

Data Index: 557218 (C4 (Web Text))

Max Activating Token Index: 328

Text #14

Max Range: 1.8422. Min Range: -1.8422

Max Act: 1.5167. Min Act: -0.0001

Data Index: 736076 (C4 (Web Text))

Max Activating Token Index: 215

Text #15

Max Range: 1.8422. Min Range: -1.8422

Max Act: 1.4940. Min Act: -0.0001

Data Index: 1185803 (C4 (Web Text))

Max Activating Token Index: 955

Text #16

Max Range: 1.8422. Min Range: -1.8422

Max Act: 1.4869. Min Act: -0.0001

Data Index: 70720 (C4 (Web Text))

Max Activating Token Index: 709

Text #17

Max Range: 1.8422. Min Range: -1.8422

Max Act: 1.5075. Min Act: -0.0001

Data Index: 883438 (C4 (Web Text))

Max Activating Token Index: 802

Text #18

Max Range: 1.8422. Min Range: -1.8422

Max Act: 1.4820. Min Act: -0.0001

Data Index: 775663 (C4 (Web Text))

Max Activating Token Index: 792

Text #19

Max Range: 1.8422. Min Range: -1.8422

Max Act: 1.4732. Min Act: -0.0001

Data Index: 273282 (C4 (Web Text))

Max Activating Token Index: 249