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

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

Neuron 2567 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0492. Min Range: -1.0492

Max Act: 1.0492. Min Act: -0.0002

Data Index: 665942 (C4 (Web Text))

Max Activating Token Index: 262

Text #1

Max Range: 1.0492. Min Range: -1.0492

Max Act: 1.0052. Min Act: -0.0002

Data Index: 802549 (C4 (Web Text))

Max Activating Token Index: 280

Text #2

Max Range: 1.0492. Min Range: -1.0492

Max Act: 0.8909. Min Act: -0.0002

Data Index: 1303575 (C4 (Web Text))

Max Activating Token Index: 684

Text #3

Max Range: 1.0492. Min Range: -1.0492

Max Act: 0.8798. Min Act: -0.0002

Data Index: 5334 (C4 (Web Text))

Max Activating Token Index: 455

Text #4

Max Range: 1.0492. Min Range: -1.0492

Max Act: 0.9082. Min Act: -0.0002

Data Index: 1049469 (C4 (Web Text))

Max Activating Token Index: 314

Text #5

Max Range: 1.0492. Min Range: -1.0492

Max Act: 0.8856. Min Act: -0.0002

Data Index: 367055 (C4 (Web Text))

Max Activating Token Index: 628

Text #6

Max Range: 1.0492. Min Range: -1.0492

Max Act: 0.8883. Min Act: -0.0002

Data Index: 504110 (C4 (Web Text))

Max Activating Token Index: 302

Text #7

Max Range: 1.0492. Min Range: -1.0492

Max Act: 0.8647. Min Act: -0.0002

Data Index: 871534 (C4 (Web Text))

Max Activating Token Index: 392

Text #8

Max Range: 1.0492. Min Range: -1.0492

Max Act: 0.8352. Min Act: -0.0002

Data Index: 492785 (C4 (Web Text))

Max Activating Token Index: 748

Text #9

Max Range: 1.0492. Min Range: -1.0492

Max Act: 0.8446. Min Act: -0.0002

Data Index: 166351 (C4 (Web Text))

Max Activating Token Index: 259

Text #10

Max Range: 1.0492. Min Range: -1.0492

Max Act: 0.8240. Min Act: -0.0002

Data Index: 1091733 (C4 (Web Text))

Max Activating Token Index: 297

Text #11

Max Range: 1.0492. Min Range: -1.0492

Max Act: 0.8528. Min Act: -0.0002

Data Index: 406539 (C4 (Web Text))

Max Activating Token Index: 307

Text #12

Max Range: 1.0492. Min Range: -1.0492

Max Act: 0.7688. Min Act: -0.0002

Data Index: 1062630 (C4 (Web Text))

Max Activating Token Index: 346

Text #13

Max Range: 1.0492. Min Range: -1.0492

Max Act: 0.7889. Min Act: -0.0002

Data Index: 17512 (C4 (Web Text))

Max Activating Token Index: 484

Text #14

Max Range: 1.0492. Min Range: -1.0492

Max Act: 0.7877. Min Act: -0.0002

Data Index: 320196 (C4 (Web Text))

Max Activating Token Index: 153

Text #15

Max Range: 1.0492. Min Range: -1.0492

Max Act: 0.7766. Min Act: -0.0002

Data Index: 460691 (C4 (Web Text))

Max Activating Token Index: 925

Text #16

Max Range: 1.0492. Min Range: -1.0492

Max Act: 0.7685. Min Act: -0.0002

Data Index: 135980 (C4 (Web Text))

Max Activating Token Index: 360

Text #17

Max Range: 1.0492. Min Range: -1.0492

Max Act: 0.7656. Min Act: -0.0002

Data Index: 1202357 (C4 (Web Text))

Max Activating Token Index: 145

Text #18

Max Range: 1.0492. Min Range: -1.0492

Max Act: 0.7854. Min Act: -0.0002

Data Index: 711875 (C4 (Web Text))

Max Activating Token Index: 412

Text #19

Max Range: 1.0492. Min Range: -1.0492

Max Act: 0.7862. Min Act: -0.0002

Data Index: 1206048 (C4 (Web Text))

Max Activating Token Index: 25