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

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

Neuron 775 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3743. Min Range: -0.3743

Max Act: 0.3743. Min Act: -0.0000

Data Index: 693006 (C4 (Web Text))

Max Activating Token Index: 655

Text #1

Max Range: 0.3743. Min Range: -0.3743

Max Act: 0.3340. Min Act: -0.0000

Data Index: 1352008 (C4 (Web Text))

Max Activating Token Index: 515

Text #2

Max Range: 0.3743. Min Range: -0.3743

Max Act: 0.3098. Min Act: -0.0000

Data Index: 719236 (C4 (Web Text))

Max Activating Token Index: 201

Text #3

Max Range: 0.3743. Min Range: -0.3743

Max Act: 0.3221. Min Act: -0.0000

Data Index: 1207359 (C4 (Web Text))

Max Activating Token Index: 882

Text #4

Max Range: 0.3743. Min Range: -0.3743

Max Act: 0.3443. Min Act: -0.0000

Data Index: 984959 (C4 (Web Text))

Max Activating Token Index: 116

Text #5

Max Range: 0.3743. Min Range: -0.3743

Max Act: 0.3148. Min Act: -0.0000

Data Index: 1188229 (C4 (Web Text))

Max Activating Token Index: 770

Text #6

Max Range: 0.3743. Min Range: -0.3743

Max Act: 0.2864. Min Act: -0.0000

Data Index: 1359269 (C4 (Web Text))

Max Activating Token Index: 912

Text #7

Max Range: 0.3743. Min Range: -0.3743

Max Act: 0.2854. Min Act: -0.0000

Data Index: 528362 (C4 (Web Text))

Max Activating Token Index: 654

Text #8

Max Range: 0.3743. Min Range: -0.3743

Max Act: 0.2773. Min Act: -0.0000

Data Index: 129432 (C4 (Web Text))

Max Activating Token Index: 138

Text #9

Max Range: 0.3743. Min Range: -0.3743

Max Act: 0.2929. Min Act: -0.0000

Data Index: 413509 (C4 (Web Text))

Max Activating Token Index: 638

Text #10

Max Range: 0.3743. Min Range: -0.3743

Max Act: 0.2644. Min Act: -0.0000

Data Index: 869918 (C4 (Web Text))

Max Activating Token Index: 949

Text #11

Max Range: 0.3743. Min Range: -0.3743

Max Act: 0.2680. Min Act: -0.0000

Data Index: 970238 (C4 (Web Text))

Max Activating Token Index: 632

Text #12

Max Range: 0.3743. Min Range: -0.3743

Max Act: 0.2394. Min Act: -0.0000

Data Index: 1042114 (C4 (Web Text))

Max Activating Token Index: 796

Text #13

Max Range: 0.3743. Min Range: -0.3743

Max Act: 0.2905. Min Act: -0.0000

Data Index: 1015080 (C4 (Web Text))

Max Activating Token Index: 417

Text #14

Max Range: 0.3743. Min Range: -0.3743

Max Act: 0.2823. Min Act: -0.0000

Data Index: 742432 (C4 (Web Text))

Max Activating Token Index: 385

Text #15

Max Range: 0.3743. Min Range: -0.3743

Max Act: 0.2659. Min Act: -0.0000

Data Index: 261127 (C4 (Web Text))

Max Activating Token Index: 569

Text #16

Max Range: 0.3743. Min Range: -0.3743

Max Act: 0.2701. Min Act: -0.0000

Data Index: 7285 (C4 (Web Text))

Max Activating Token Index: 494

Text #17

Max Range: 0.3743. Min Range: -0.3743

Max Act: 0.2611. Min Act: -0.0000

Data Index: 477954 (C4 (Web Text))

Max Activating Token Index: 330

Text #18

Max Range: 0.3743. Min Range: -0.3743

Max Act: 0.2691. Min Act: -0.0000

Data Index: 1157067 (C4 (Web Text))

Max Activating Token Index: 342

Text #19

Max Range: 0.3743. Min Range: -0.3743

Max Act: 0.2655. Min Act: -0.0000

Data Index: 248093 (C4 (Web Text))

Max Activating Token Index: 582