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

Dataset: The Pile

Neuron 1752 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8032. Min Range: -3.8032

Max Act: 3.8032. Min Act: -0.0000

Data Index: 1547789 (The Pile)

Max Activating Token Index: 93

Text #1

Max Range: 3.8032. Min Range: -3.8032

Max Act: 3.2584. Min Act: -0.0000

Data Index: 791183 (The Pile)

Max Activating Token Index: 908

Text #2

Max Range: 3.8032. Min Range: -3.8032

Max Act: 3.5312. Min Act: -0.0000

Data Index: 394114 (The Pile)

Max Activating Token Index: 131

Text #3

Max Range: 3.8032. Min Range: -3.8032

Max Act: 3.6077. Min Act: -0.0000

Data Index: 424724 (The Pile)

Max Activating Token Index: 388

Text #4

Max Range: 3.8032. Min Range: -3.8032

Max Act: 3.1270. Min Act: -0.0000

Data Index: 443964 (The Pile)

Max Activating Token Index: 161

Text #5

Max Range: 3.8032. Min Range: -3.8032

Max Act: 3.3564. Min Act: -0.0000

Data Index: 1100937 (The Pile)

Max Activating Token Index: 353

Text #6

Max Range: 3.8032. Min Range: -3.8032

Max Act: 3.0543. Min Act: -0.0000

Data Index: 543306 (The Pile)

Max Activating Token Index: 416

Text #7

Max Range: 3.8032. Min Range: -3.8032

Max Act: 3.0496. Min Act: -0.0000

Data Index: 358813 (The Pile)

Max Activating Token Index: 119

Text #8

Max Range: 3.8032. Min Range: -3.8032

Max Act: 3.1555. Min Act: -0.0000

Data Index: 1295577 (The Pile)

Max Activating Token Index: 147

Text #9

Max Range: 3.8032. Min Range: -3.8032

Max Act: 3.1091. Min Act: -0.0000

Data Index: 1641032 (The Pile)

Max Activating Token Index: 86

Text #10

Max Range: 3.8032. Min Range: -3.8032

Max Act: 2.8074. Min Act: -0.0000

Data Index: 424742 (The Pile)

Max Activating Token Index: 561

Text #11

Max Range: 3.8032. Min Range: -3.8032

Max Act: 2.9381. Min Act: -0.0000

Data Index: 1595184 (The Pile)

Max Activating Token Index: 398

Text #12

Max Range: 3.8032. Min Range: -3.8032

Max Act: 2.7675. Min Act: -0.0000

Data Index: 1350804 (The Pile)

Max Activating Token Index: 842

Text #13

Max Range: 3.8032. Min Range: -3.8032

Max Act: 3.2014. Min Act: -0.0000

Data Index: 884164 (The Pile)

Max Activating Token Index: 443

Text #14

Max Range: 3.8032. Min Range: -3.8032

Max Act: 2.8594. Min Act: -0.0000

Data Index: 1627249 (The Pile)

Max Activating Token Index: 974

Text #15

Max Range: 3.8032. Min Range: -3.8032

Max Act: 2.8578. Min Act: -0.0000

Data Index: 1853162 (The Pile)

Max Activating Token Index: 122

Text #16

Max Range: 3.8032. Min Range: -3.8032

Max Act: 2.7765. Min Act: -0.0000

Data Index: 1956947 (The Pile)

Max Activating Token Index: 879

Text #17

Max Range: 3.8032. Min Range: -3.8032

Max Act: 2.7971. Min Act: -0.0000

Data Index: 1049543 (The Pile)

Max Activating Token Index: 256

Text #18

Max Range: 3.8032. Min Range: -3.8032

Max Act: 2.1651. Min Act: -0.0000

Data Index: 1746706 (The Pile)

Max Activating Token Index: 713

Text #19

Max Range: 3.8032. Min Range: -3.8032

Max Act: 3.0427. Min Act: -0.0000

Data Index: 23323 (The Pile)

Max Activating Token Index: 271