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

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

Neuron 4506 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4872. Min Range: -1.4872

Max Act: 1.4628. Min Act: -0.0000

Data Index: 1311945 (C4 (Web Text))

Max Activating Token Index: 322

Text #1

Max Range: 1.4872. Min Range: -1.4872

Max Act: 1.4143. Min Act: -0.0000

Data Index: 72682 (C4 (Web Text))

Max Activating Token Index: 791

Text #2

Max Range: 1.4872. Min Range: -1.4872

Max Act: 1.4872. Min Act: -0.0000

Data Index: 114911 (C4 (Web Text))

Max Activating Token Index: 930

Text #3

Max Range: 1.4872. Min Range: -1.4872

Max Act: 1.4798. Min Act: -0.0000

Data Index: 1191670 (C4 (Web Text))

Max Activating Token Index: 704

Text #4

Max Range: 1.4872. Min Range: -1.4872

Max Act: 1.4192. Min Act: -0.0000

Data Index: 627214 (C4 (Web Text))

Max Activating Token Index: 735

Text #5

Max Range: 1.4872. Min Range: -1.4872

Max Act: 1.4770. Min Act: -0.0000

Data Index: 168879 (C4 (Web Text))

Max Activating Token Index: 900

Text #6

Max Range: 1.4872. Min Range: -1.4872

Max Act: 1.3024. Min Act: -0.0000

Data Index: 568063 (C4 (Web Text))

Max Activating Token Index: 760

Text #7

Max Range: 1.4872. Min Range: -1.4872

Max Act: 1.3553. Min Act: -0.0000

Data Index: 394389 (C4 (Web Text))

Max Activating Token Index: 754

Text #8

Max Range: 1.4872. Min Range: -1.4872

Max Act: 1.3112. Min Act: -0.0000

Data Index: 507782 (C4 (Web Text))

Max Activating Token Index: 468

Text #9

Max Range: 1.4872. Min Range: -1.4872

Max Act: 1.2532. Min Act: -0.0000

Data Index: 244116 (C4 (Web Text))

Max Activating Token Index: 566

Text #10

Max Range: 1.4872. Min Range: -1.4872

Max Act: 1.3749. Min Act: -0.0000

Data Index: 1357868 (C4 (Web Text))

Max Activating Token Index: 923

Text #11

Max Range: 1.4872. Min Range: -1.4872

Max Act: 1.2835. Min Act: -0.0000

Data Index: 919018 (C4 (Web Text))

Max Activating Token Index: 403

Text #12

Max Range: 1.4872. Min Range: -1.4872

Max Act: 1.2458. Min Act: -0.0000

Data Index: 647857 (C4 (Web Text))

Max Activating Token Index: 976

Text #13

Max Range: 1.4872. Min Range: -1.4872

Max Act: 1.2894. Min Act: -0.0000

Data Index: 279579 (C4 (Web Text))

Max Activating Token Index: 166

Text #14

Max Range: 1.4872. Min Range: -1.4872

Max Act: 1.2212. Min Act: -0.0000

Data Index: 335919 (C4 (Web Text))

Max Activating Token Index: 861

Text #15

Max Range: 1.4872. Min Range: -1.4872

Max Act: 1.3020. Min Act: -0.0000

Data Index: 273452 (C4 (Web Text))

Max Activating Token Index: 813

Text #16

Max Range: 1.4872. Min Range: -1.4872

Max Act: 1.2230. Min Act: -0.0000

Data Index: 330755 (C4 (Web Text))

Max Activating Token Index: 1008

Text #17

Max Range: 1.4872. Min Range: -1.4872

Max Act: 1.2543. Min Act: -0.0000

Data Index: 401199 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 1.4872. Min Range: -1.4872

Max Act: 1.3743. Min Act: -0.0000

Data Index: 1313926 (C4 (Web Text))

Max Activating Token Index: 986

Text #19

Max Range: 1.4872. Min Range: -1.4872

Max Act: 1.2520. Min Act: -0.0000

Data Index: 685513 (C4 (Web Text))

Max Activating Token Index: 603