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

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

Neuron 4042 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5954. Min Range: -0.5954

Max Act: 0.5700. Min Act: -0.0000

Data Index: 896495 (C4 (Web Text))

Max Activating Token Index: 498

Text #1

Max Range: 0.5954. Min Range: -0.5954

Max Act: 0.5954. Min Act: -0.0000

Data Index: 1117564 (C4 (Web Text))

Max Activating Token Index: 209

Text #2

Max Range: 0.5954. Min Range: -0.5954

Max Act: 0.5393. Min Act: -0.0000

Data Index: 502084 (C4 (Web Text))

Max Activating Token Index: 241

Text #3

Max Range: 0.5954. Min Range: -0.5954

Max Act: 0.5371. Min Act: -0.0000

Data Index: 823360 (C4 (Web Text))

Max Activating Token Index: 799

Text #4

Max Range: 0.5954. Min Range: -0.5954

Max Act: 0.4694. Min Act: -0.0000

Data Index: 697509 (C4 (Web Text))

Max Activating Token Index: 721

Text #5

Max Range: 0.5954. Min Range: -0.5954

Max Act: 0.4998. Min Act: -0.0000

Data Index: 1124843 (C4 (Web Text))

Max Activating Token Index: 441

Text #6

Max Range: 0.5954. Min Range: -0.5954

Max Act: 0.5079. Min Act: -0.0000

Data Index: 404891 (C4 (Web Text))

Max Activating Token Index: 389

Text #7

Max Range: 0.5954. Min Range: -0.5954

Max Act: 0.4903. Min Act: -0.0000

Data Index: 1102193 (C4 (Web Text))

Max Activating Token Index: 72

Text #8

Max Range: 0.5954. Min Range: -0.5954

Max Act: 0.4893. Min Act: -0.0000

Data Index: 1062661 (C4 (Web Text))

Max Activating Token Index: 570

Text #9

Max Range: 0.5954. Min Range: -0.5954

Max Act: 0.5030. Min Act: -0.0000

Data Index: 1282180 (C4 (Web Text))

Max Activating Token Index: 679

Text #10

Max Range: 0.5954. Min Range: -0.5954

Max Act: 0.4698. Min Act: -0.0000

Data Index: 347501 (C4 (Web Text))

Max Activating Token Index: 316

Text #11

Max Range: 0.5954. Min Range: -0.5954

Max Act: 0.4653. Min Act: -0.0000

Data Index: 48719 (C4 (Web Text))

Max Activating Token Index: 530

Text #12

Max Range: 0.5954. Min Range: -0.5954

Max Act: 0.4767. Min Act: -0.0000

Data Index: 920395 (C4 (Web Text))

Max Activating Token Index: 964

Text #13

Max Range: 0.5954. Min Range: -0.5954

Max Act: 0.4576. Min Act: -0.0000

Data Index: 431503 (C4 (Web Text))

Max Activating Token Index: 755

Text #14

Max Range: 0.5954. Min Range: -0.5954

Max Act: 0.4566. Min Act: -0.0000

Data Index: 78666 (C4 (Web Text))

Max Activating Token Index: 961

Text #15

Max Range: 0.5954. Min Range: -0.5954

Max Act: 0.4504. Min Act: -0.0000

Data Index: 1018733 (C4 (Web Text))

Max Activating Token Index: 694

Text #16

Max Range: 0.5954. Min Range: -0.5954

Max Act: 0.4730. Min Act: -0.0000

Data Index: 215478 (C4 (Web Text))

Max Activating Token Index: 177

Text #17

Max Range: 0.5954. Min Range: -0.5954

Max Act: 0.4429. Min Act: -0.0000

Data Index: 750020 (C4 (Web Text))

Max Activating Token Index: 310

Text #18

Max Range: 0.5954. Min Range: -0.5954

Max Act: 0.4371. Min Act: -0.0000

Data Index: 1083905 (C4 (Web Text))

Max Activating Token Index: 689

Text #19

Max Range: 0.5954. Min Range: -0.5954

Max Act: 0.4374. Min Act: -0.0000

Data Index: 789755 (C4 (Web Text))

Max Activating Token Index: 745