Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 107 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.7733. Min Range: -1.7733

Max Act: 1.7733. Min Act: -0.0001

Data Index: 747298 (C4 (Web Text))

Max Activating Token Index: 594

Text #1

Max Range: 1.7733. Min Range: -1.7733

Max Act: 1.4896. Min Act: -0.0001

Data Index: 67702 (C4 (Web Text))

Max Activating Token Index: 941

Text #2

Max Range: 1.7733. Min Range: -1.7733

Max Act: 1.4725. Min Act: -0.0001

Data Index: 143379 (C4 (Web Text))

Max Activating Token Index: 156

Text #3

Max Range: 1.7733. Min Range: -1.7733

Max Act: 1.3248. Min Act: -0.0001

Data Index: 103896 (C4 (Web Text))

Max Activating Token Index: 661

Text #4

Max Range: 1.7733. Min Range: -1.7733

Max Act: 1.4464. Min Act: -0.0001

Data Index: 114256 (C4 (Web Text))

Max Activating Token Index: 558

Text #5

Max Range: 1.7733. Min Range: -1.7733

Max Act: 1.2766. Min Act: -0.0001

Data Index: 295658 (C4 (Web Text))

Max Activating Token Index: 663

Text #6

Max Range: 1.7733. Min Range: -1.7733

Max Act: 1.2896. Min Act: -0.0001

Data Index: 256100 (C4 (Web Text))

Max Activating Token Index: 46

Text #7

Max Range: 1.7733. Min Range: -1.7733

Max Act: 1.3663. Min Act: -0.0001

Data Index: 1180245 (C4 (Web Text))

Max Activating Token Index: 795

Text #8

Max Range: 1.7733. Min Range: -1.7733

Max Act: 1.3140. Min Act: -0.0001

Data Index: 179000 (C4 (Web Text))

Max Activating Token Index: 791

Text #9

Max Range: 1.7733. Min Range: -1.7733

Max Act: 1.3088. Min Act: -0.0001

Data Index: 501607 (C4 (Web Text))

Max Activating Token Index: 485

Text #10

Max Range: 1.7733. Min Range: -1.7733

Max Act: 1.2145. Min Act: -0.0001

Data Index: 1206797 (C4 (Web Text))

Max Activating Token Index: 16

Text #11

Max Range: 1.7733. Min Range: -1.7733

Max Act: 1.2500. Min Act: -0.0001

Data Index: 306435 (C4 (Web Text))

Max Activating Token Index: 818

Text #12

Max Range: 1.7733. Min Range: -1.7733

Max Act: 1.2449. Min Act: -0.0001

Data Index: 469678 (C4 (Web Text))

Max Activating Token Index: 94

Text #13

Max Range: 1.7733. Min Range: -1.7733

Max Act: 1.1750. Min Act: -0.0001

Data Index: 509269 (C4 (Web Text))

Max Activating Token Index: 501

Text #14

Max Range: 1.7733. Min Range: -1.7733

Max Act: 1.1805. Min Act: -0.0001

Data Index: 714489 (C4 (Web Text))

Max Activating Token Index: 1021

Text #15

Max Range: 1.7733. Min Range: -1.7733

Max Act: 1.1414. Min Act: -0.0001

Data Index: 777103 (C4 (Web Text))

Max Activating Token Index: 823

Text #16

Max Range: 1.7733. Min Range: -1.7733

Max Act: 1.1751. Min Act: -0.0001

Data Index: 1035707 (C4 (Web Text))

Max Activating Token Index: 684

Text #17

Max Range: 1.7733. Min Range: -1.7733

Max Act: 1.1110. Min Act: -0.0001

Data Index: 338142 (C4 (Web Text))

Max Activating Token Index: 440

Text #18

Max Range: 1.7733. Min Range: -1.7733

Max Act: 0.9989. Min Act: -0.0001

Data Index: 1394434 (Python Code)

Max Activating Token Index: 945

Text #19

Max Range: 1.7733. Min Range: -1.7733

Max Act: 1.0488. Min Act: -0.0001

Data Index: 1645592 (Python Code)

Max Activating Token Index: 455