Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 783 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1165. Min Range: -0.1165

Max Act: 0.1165. Min Act: -0.0001

Data Index: 1089179 (C4 (Web Text))

Max Activating Token Index: 1018

Text #1

Max Range: 0.1165. Min Range: -0.1165

Max Act: 0.0863. Min Act: -0.0001

Data Index: 769369 (C4 (Web Text))

Max Activating Token Index: 183

Text #2

Max Range: 0.1165. Min Range: -0.1165

Max Act: 0.0822. Min Act: -0.0001

Data Index: 209646 (C4 (Web Text))

Max Activating Token Index: 614

Text #3

Max Range: 0.1165. Min Range: -0.1165

Max Act: 0.0822. Min Act: -0.0000

Data Index: 724825 (C4 (Web Text))

Max Activating Token Index: 712

Text #4

Max Range: 0.1165. Min Range: -0.1165

Max Act: 0.0732. Min Act: -0.0001

Data Index: 1220490 (C4 (Web Text))

Max Activating Token Index: 290

Text #5

Max Range: 0.1165. Min Range: -0.1165

Max Act: 0.0788. Min Act: -0.0001

Data Index: 322772 (C4 (Web Text))

Max Activating Token Index: 564

Text #6

Max Range: 0.1165. Min Range: -0.1165

Max Act: 0.0775. Min Act: -0.0001

Data Index: 1287225 (C4 (Web Text))

Max Activating Token Index: 724

Text #7

Max Range: 0.1165. Min Range: -0.1165

Max Act: 0.0754. Min Act: -0.0001

Data Index: 581265 (C4 (Web Text))

Max Activating Token Index: 130

Text #8

Max Range: 0.1165. Min Range: -0.1165

Max Act: 0.0748. Min Act: -0.0001

Data Index: 355421 (C4 (Web Text))

Max Activating Token Index: 240

Text #9

Max Range: 0.1165. Min Range: -0.1165

Max Act: 0.0706. Min Act: -0.0001

Data Index: 1574636 (Python Code)

Max Activating Token Index: 928

Text #10

Max Range: 0.1165. Min Range: -0.1165

Max Act: 0.0751. Min Act: -0.0001

Data Index: 984395 (C4 (Web Text))

Max Activating Token Index: 150

Text #11

Max Range: 0.1165. Min Range: -0.1165

Max Act: 0.0739. Min Act: -0.0001

Data Index: 1223871 (C4 (Web Text))

Max Activating Token Index: 818

Text #12

Max Range: 0.1165. Min Range: -0.1165

Max Act: 0.0755. Min Act: -0.0001

Data Index: 546401 (C4 (Web Text))

Max Activating Token Index: 820

Text #13

Max Range: 0.1165. Min Range: -0.1165

Max Act: 0.0725. Min Act: -0.0001

Data Index: 104205 (C4 (Web Text))

Max Activating Token Index: 409

Text #14

Max Range: 0.1165. Min Range: -0.1165

Max Act: 0.0719. Min Act: -0.0001

Data Index: 1059581 (C4 (Web Text))

Max Activating Token Index: 776

Text #15

Max Range: 0.1165. Min Range: -0.1165

Max Act: 0.0691. Min Act: -0.0001

Data Index: 503785 (C4 (Web Text))

Max Activating Token Index: 526

Text #16

Max Range: 0.1165. Min Range: -0.1165

Max Act: 0.0731. Min Act: -0.0001

Data Index: 92032 (C4 (Web Text))

Max Activating Token Index: 852

Text #17

Max Range: 0.1165. Min Range: -0.1165

Max Act: 0.0695. Min Act: -0.0000

Data Index: 168916 (C4 (Web Text))

Max Activating Token Index: 843

Text #18

Max Range: 0.1165. Min Range: -0.1165

Max Act: 0.0701. Min Act: -0.0001

Data Index: 33462 (C4 (Web Text))

Max Activating Token Index: 990

Text #19

Max Range: 0.1165. Min Range: -0.1165

Max Act: 0.0698. Min Act: -0.0001

Data Index: 890483 (C4 (Web Text))

Max Activating Token Index: 912