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

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

Neuron 1185 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: 1.1780. Min Range: -1.1780

Max Act: 1.1780. Min Act: -0.0000

Data Index: 723804 (C4 (Web Text))

Max Activating Token Index: 103

Text #1

Max Range: 1.1780. Min Range: -1.1780

Max Act: 1.1088. Min Act: -0.0000

Data Index: 7809 (C4 (Web Text))

Max Activating Token Index: 902

Text #2

Max Range: 1.1780. Min Range: -1.1780

Max Act: 1.0760. Min Act: -0.0000

Data Index: 122737 (C4 (Web Text))

Max Activating Token Index: 669

Text #3

Max Range: 1.1780. Min Range: -1.1780

Max Act: 1.1148. Min Act: -0.0000

Data Index: 1030817 (C4 (Web Text))

Max Activating Token Index: 633

Text #4

Max Range: 1.1780. Min Range: -1.1780

Max Act: 1.0304. Min Act: -0.0000

Data Index: 1299076 (C4 (Web Text))

Max Activating Token Index: 503

Text #5

Max Range: 1.1780. Min Range: -1.1780

Max Act: 0.9512. Min Act: -0.0000

Data Index: 1090095 (C4 (Web Text))

Max Activating Token Index: 797

Text #6

Max Range: 1.1780. Min Range: -1.1780

Max Act: 0.9728. Min Act: -0.0000

Data Index: 951586 (C4 (Web Text))

Max Activating Token Index: 288

Text #7

Max Range: 1.1780. Min Range: -1.1780

Max Act: 1.0028. Min Act: -0.0000

Data Index: 1287692 (C4 (Web Text))

Max Activating Token Index: 526

Text #8

Max Range: 1.1780. Min Range: -1.1780

Max Act: 0.9231. Min Act: -0.0000

Data Index: 103590 (C4 (Web Text))

Max Activating Token Index: 357

Text #9

Max Range: 1.1780. Min Range: -1.1780

Max Act: 1.0048. Min Act: -0.0000

Data Index: 832911 (C4 (Web Text))

Max Activating Token Index: 357

Text #10

Max Range: 1.1780. Min Range: -1.1780

Max Act: 0.9713. Min Act: -0.0000

Data Index: 454063 (C4 (Web Text))

Max Activating Token Index: 496

Text #11

Max Range: 1.1780. Min Range: -1.1780

Max Act: 1.0017. Min Act: -0.0000

Data Index: 1055029 (C4 (Web Text))

Max Activating Token Index: 264

Text #12

Max Range: 1.1780. Min Range: -1.1780

Max Act: 0.9606. Min Act: -0.0000

Data Index: 1262236 (C4 (Web Text))

Max Activating Token Index: 795

Text #13

Max Range: 1.1780. Min Range: -1.1780

Max Act: 0.9476. Min Act: -0.0000

Data Index: 1284481 (C4 (Web Text))

Max Activating Token Index: 509

Text #14

Max Range: 1.1780. Min Range: -1.1780

Max Act: 0.9503. Min Act: -0.0000

Data Index: 872126 (C4 (Web Text))

Max Activating Token Index: 491

Text #15

Max Range: 1.1780. Min Range: -1.1780

Max Act: 0.9450. Min Act: -0.0000

Data Index: 99201 (C4 (Web Text))

Max Activating Token Index: 530

Text #16

Max Range: 1.1780. Min Range: -1.1780

Max Act: 0.9770. Min Act: -0.0000

Data Index: 795497 (C4 (Web Text))

Max Activating Token Index: 419

Text #17

Max Range: 1.1780. Min Range: -1.1780

Max Act: 0.8780. Min Act: -0.0000

Data Index: 334760 (C4 (Web Text))

Max Activating Token Index: 854

Text #18

Max Range: 1.1780. Min Range: -1.1780

Max Act: 0.9687. Min Act: -0.0000

Data Index: 1114190 (C4 (Web Text))

Max Activating Token Index: 505

Text #19

Max Range: 1.1780. Min Range: -1.1780

Max Act: 0.9262. Min Act: -0.0000

Data Index: 691287 (C4 (Web Text))

Max Activating Token Index: 970