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

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

Neuron 2869 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1571. Min Range: -2.1571

Max Act: 2.1571. Min Act: -0.0000

Data Index: 157640 (C4 (Web Text))

Max Activating Token Index: 907

Text #1

Max Range: 2.1571. Min Range: -2.1571

Max Act: 1.9413. Min Act: -0.0000

Data Index: 769952 (C4 (Web Text))

Max Activating Token Index: 393

Text #2

Max Range: 2.1571. Min Range: -2.1571

Max Act: 1.8352. Min Act: -0.0000

Data Index: 954597 (C4 (Web Text))

Max Activating Token Index: 237

Text #3

Max Range: 2.1571. Min Range: -2.1571

Max Act: 1.8931. Min Act: -0.0000

Data Index: 1235255 (C4 (Web Text))

Max Activating Token Index: 504

Text #4

Max Range: 2.1571. Min Range: -2.1571

Max Act: 1.8165. Min Act: -0.0000

Data Index: 396639 (C4 (Web Text))

Max Activating Token Index: 748

Text #5

Max Range: 2.1571. Min Range: -2.1571

Max Act: 1.6821. Min Act: -0.0000

Data Index: 415639 (C4 (Web Text))

Max Activating Token Index: 132

Text #6

Max Range: 2.1571. Min Range: -2.1571

Max Act: 1.7949. Min Act: -0.0000

Data Index: 57790 (C4 (Web Text))

Max Activating Token Index: 327

Text #7

Max Range: 2.1571. Min Range: -2.1571

Max Act: 1.6686. Min Act: -0.0000

Data Index: 1181828 (C4 (Web Text))

Max Activating Token Index: 621

Text #8

Max Range: 2.1571. Min Range: -2.1571

Max Act: 1.5664. Min Act: -0.0000

Data Index: 658640 (C4 (Web Text))

Max Activating Token Index: 404

Text #9

Max Range: 2.1571. Min Range: -2.1571

Max Act: 1.7400. Min Act: -0.0000

Data Index: 213292 (C4 (Web Text))

Max Activating Token Index: 379

Text #10

Max Range: 2.1571. Min Range: -2.1571

Max Act: 1.5396. Min Act: -0.0000

Data Index: 345346 (C4 (Web Text))

Max Activating Token Index: 851

Text #11

Max Range: 2.1571. Min Range: -2.1571

Max Act: 1.6412. Min Act: -0.0000

Data Index: 557925 (C4 (Web Text))

Max Activating Token Index: 314

Text #12

Max Range: 2.1571. Min Range: -2.1571

Max Act: 1.5976. Min Act: -0.0000

Data Index: 313813 (C4 (Web Text))

Max Activating Token Index: 928

Text #13

Max Range: 2.1571. Min Range: -2.1571

Max Act: 1.5958. Min Act: -0.0000

Data Index: 260083 (C4 (Web Text))

Max Activating Token Index: 291

Text #14

Max Range: 2.1571. Min Range: -2.1571

Max Act: 1.5993. Min Act: -0.0000

Data Index: 1062764 (C4 (Web Text))

Max Activating Token Index: 201

Text #15

Max Range: 2.1571. Min Range: -2.1571

Max Act: 1.4944. Min Act: -0.0000

Data Index: 906389 (C4 (Web Text))

Max Activating Token Index: 616

Text #16

Max Range: 2.1571. Min Range: -2.1571

Max Act: 1.5664. Min Act: -0.0000

Data Index: 909134 (C4 (Web Text))

Max Activating Token Index: 484

Text #17

Max Range: 2.1571. Min Range: -2.1571

Max Act: 1.6439. Min Act: -0.0000

Data Index: 1016296 (C4 (Web Text))

Max Activating Token Index: 406

Text #18

Max Range: 2.1571. Min Range: -2.1571

Max Act: 1.5447. Min Act: -0.0000

Data Index: 659800 (C4 (Web Text))

Max Activating Token Index: 840

Text #19

Max Range: 2.1571. Min Range: -2.1571

Max Act: 1.5495. Min Act: -0.0000

Data Index: 727791 (C4 (Web Text))

Max Activating Token Index: 976