Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1258 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.0686. Min Range: -1.0686

Max Act: 1.0686. Min Act: -0.0001

Data Index: 811776 (C4 (Web Text))

Max Activating Token Index: 103

Text #1

Max Range: 1.0686. Min Range: -1.0686

Max Act: 0.9366. Min Act: -0.0001

Data Index: 1301103 (C4 (Web Text))

Max Activating Token Index: 475

Text #2

Max Range: 1.0686. Min Range: -1.0686

Max Act: 0.9430. Min Act: -0.0001

Data Index: 274907 (C4 (Web Text))

Max Activating Token Index: 894

Text #3

Max Range: 1.0686. Min Range: -1.0686

Max Act: 0.9299. Min Act: -0.0001

Data Index: 1230453 (C4 (Web Text))

Max Activating Token Index: 370

Text #4

Max Range: 1.0686. Min Range: -1.0686

Max Act: 0.8484. Min Act: -0.0002

Data Index: 834544 (C4 (Web Text))

Max Activating Token Index: 754

Text #5

Max Range: 1.0686. Min Range: -1.0686

Max Act: 0.8967. Min Act: -0.0001

Data Index: 696461 (C4 (Web Text))

Max Activating Token Index: 733

Text #6

Max Range: 1.0686. Min Range: -1.0686

Max Act: 0.8614. Min Act: -0.0001

Data Index: 371123 (C4 (Web Text))

Max Activating Token Index: 636

Text #7

Max Range: 1.0686. Min Range: -1.0686

Max Act: 0.9155. Min Act: -0.0001

Data Index: 14779 (C4 (Web Text))

Max Activating Token Index: 895

Text #8

Max Range: 1.0686. Min Range: -1.0686

Max Act: 0.8540. Min Act: -0.0002

Data Index: 798968 (C4 (Web Text))

Max Activating Token Index: 393

Text #9

Max Range: 1.0686. Min Range: -1.0686

Max Act: 0.9092. Min Act: -0.0001

Data Index: 296905 (C4 (Web Text))

Max Activating Token Index: 376

Text #10

Max Range: 1.0686. Min Range: -1.0686

Max Act: 0.8443. Min Act: -0.0001

Data Index: 1225262 (C4 (Web Text))

Max Activating Token Index: 627

Text #11

Max Range: 1.0686. Min Range: -1.0686

Max Act: 0.8200. Min Act: -0.0001

Data Index: 365795 (C4 (Web Text))

Max Activating Token Index: 163

Text #12

Max Range: 1.0686. Min Range: -1.0686

Max Act: 0.8701. Min Act: -0.0001

Data Index: 1220686 (C4 (Web Text))

Max Activating Token Index: 498

Text #13

Max Range: 1.0686. Min Range: -1.0686

Max Act: 0.8952. Min Act: -0.0001

Data Index: 1347632 (C4 (Web Text))

Max Activating Token Index: 984

Text #14

Max Range: 1.0686. Min Range: -1.0686

Max Act: 0.7676. Min Act: -0.0001

Data Index: 614175 (C4 (Web Text))

Max Activating Token Index: 968

Text #15

Max Range: 1.0686. Min Range: -1.0686

Max Act: 0.9882. Min Act: -0.0001

Data Index: 1209460 (C4 (Web Text))

Max Activating Token Index: 628

Text #16

Max Range: 1.0686. Min Range: -1.0686

Max Act: 0.7597. Min Act: -0.0001

Data Index: 629271 (C4 (Web Text))

Max Activating Token Index: 535

Text #17

Max Range: 1.0686. Min Range: -1.0686

Max Act: 0.8929. Min Act: -0.0001

Data Index: 1119751 (C4 (Web Text))

Max Activating Token Index: 258

Text #18

Max Range: 1.0686. Min Range: -1.0686

Max Act: 0.8834. Min Act: -0.0001

Data Index: 1055401 (C4 (Web Text))

Max Activating Token Index: 289

Text #19

Max Range: 1.0686. Min Range: -1.0686

Max Act: 0.8254. Min Act: -0.0002

Data Index: 1028060 (C4 (Web Text))

Max Activating Token Index: 9