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

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

Neuron 5051 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7693. Min Range: -1.7693

Max Act: 1.7693. Min Act: -0.0000

Data Index: 488318 (C4 (Web Text))

Max Activating Token Index: 305

Text #1

Max Range: 1.7693. Min Range: -1.7693

Max Act: 1.4721. Min Act: -0.0000

Data Index: 384832 (C4 (Web Text))

Max Activating Token Index: 574

Text #2

Max Range: 1.7693. Min Range: -1.7693

Max Act: 1.6040. Min Act: -0.0000

Data Index: 904289 (C4 (Web Text))

Max Activating Token Index: 248

Text #3

Max Range: 1.7693. Min Range: -1.7693

Max Act: 1.5054. Min Act: -0.0000

Data Index: 869054 (C4 (Web Text))

Max Activating Token Index: 655

Text #4

Max Range: 1.7693. Min Range: -1.7693

Max Act: 1.3630. Min Act: -0.0000

Data Index: 745445 (C4 (Web Text))

Max Activating Token Index: 799

Text #5

Max Range: 1.7693. Min Range: -1.7693

Max Act: 1.2487. Min Act: -0.0000

Data Index: 191012 (C4 (Web Text))

Max Activating Token Index: 968

Text #6

Max Range: 1.7693. Min Range: -1.7693

Max Act: 1.2341. Min Act: -0.0000

Data Index: 311755 (C4 (Web Text))

Max Activating Token Index: 549

Text #7

Max Range: 1.7693. Min Range: -1.7693

Max Act: 1.1965. Min Act: -0.0000

Data Index: 253981 (C4 (Web Text))

Max Activating Token Index: 285

Text #8

Max Range: 1.7693. Min Range: -1.7693

Max Act: 0.9426. Min Act: -0.0000

Data Index: 375600 (C4 (Web Text))

Max Activating Token Index: 749

Text #9

Max Range: 1.7693. Min Range: -1.7693

Max Act: 0.8927. Min Act: -0.0000

Data Index: 903525 (C4 (Web Text))

Max Activating Token Index: 628

Text #10

Max Range: 1.7693. Min Range: -1.7693

Max Act: 0.8458. Min Act: -0.0000

Data Index: 408145 (C4 (Web Text))

Max Activating Token Index: 216

Text #11

Max Range: 1.7693. Min Range: -1.7693

Max Act: 0.8878. Min Act: -0.0000

Data Index: 936506 (C4 (Web Text))

Max Activating Token Index: 618

Text #12

Max Range: 1.7693. Min Range: -1.7693

Max Act: 0.9722. Min Act: -0.0000

Data Index: 190503 (C4 (Web Text))

Max Activating Token Index: 666

Text #13

Max Range: 1.7693. Min Range: -1.7693

Max Act: 0.8700. Min Act: -0.0000

Data Index: 423634 (C4 (Web Text))

Max Activating Token Index: 674

Text #14

Max Range: 1.7693. Min Range: -1.7693

Max Act: 0.8170. Min Act: -0.0000

Data Index: 1441258 (Python Code)

Max Activating Token Index: 478

Text #15

Max Range: 1.7693. Min Range: -1.7693

Max Act: 0.8354. Min Act: -0.0000

Data Index: 325809 (C4 (Web Text))

Max Activating Token Index: 274

Text #16

Max Range: 1.7693. Min Range: -1.7693

Max Act: 0.8227. Min Act: -0.0000

Data Index: 775341 (C4 (Web Text))

Max Activating Token Index: 393

Text #17

Max Range: 1.7693. Min Range: -1.7693

Max Act: 0.7918. Min Act: -0.0000

Data Index: 2799 (C4 (Web Text))

Max Activating Token Index: 30

Text #18

Max Range: 1.7693. Min Range: -1.7693

Max Act: 0.7897. Min Act: -0.0000

Data Index: 904069 (C4 (Web Text))

Max Activating Token Index: 952

Text #19

Max Range: 1.7693. Min Range: -1.7693

Max Act: 0.8383. Min Act: -0.0000

Data Index: 173031 (C4 (Web Text))

Max Activating Token Index: 725