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

Dataset: The Pile

Neuron 1901 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9791. Min Range: -0.9791

Max Act: 0.9791. Min Act: -0.0000

Data Index: 703549 (The Pile)

Max Activating Token Index: 489

Text #1

Max Range: 0.9791. Min Range: -0.9791

Max Act: 0.9527. Min Act: -0.0000

Data Index: 215266 (The Pile)

Max Activating Token Index: 644

Text #2

Max Range: 0.9791. Min Range: -0.9791

Max Act: 0.8584. Min Act: -0.0000

Data Index: 1301298 (The Pile)

Max Activating Token Index: 184

Text #3

Max Range: 0.9791. Min Range: -0.9791

Max Act: 0.7520. Min Act: -0.0000

Data Index: 1717744 (The Pile)

Max Activating Token Index: 239

Text #4

Max Range: 0.9791. Min Range: -0.9791

Max Act: 0.6880. Min Act: -0.0000

Data Index: 1648098 (The Pile)

Max Activating Token Index: 148

Text #5

Max Range: 0.9791. Min Range: -0.9791

Max Act: 0.6608. Min Act: -0.0000

Data Index: 867552 (The Pile)

Max Activating Token Index: 490

Text #6

Max Range: 0.9791. Min Range: -0.9791

Max Act: 0.6679. Min Act: -0.0000

Data Index: 877695 (The Pile)

Max Activating Token Index: 757

Text #7

Max Range: 0.9791. Min Range: -0.9791

Max Act: 0.6815. Min Act: -0.0000

Data Index: 1757604 (The Pile)

Max Activating Token Index: 100

Text #8

Max Range: 0.9791. Min Range: -0.9791

Max Act: 0.6117. Min Act: -0.0000

Data Index: 1733048 (The Pile)

Max Activating Token Index: 473

Text #9

Max Range: 0.9791. Min Range: -0.9791

Max Act: 0.7045. Min Act: -0.0000

Data Index: 957730 (The Pile)

Max Activating Token Index: 148

Text #10

Max Range: 0.9791. Min Range: -0.9791

Max Act: 0.7372. Min Act: -0.0000

Data Index: 1178702 (The Pile)

Max Activating Token Index: 687

Text #11

Max Range: 0.9791. Min Range: -0.9791

Max Act: 0.5835. Min Act: -0.0000

Data Index: 631126 (The Pile)

Max Activating Token Index: 888

Text #12

Max Range: 0.9791. Min Range: -0.9791

Max Act: 0.5775. Min Act: -0.0000

Data Index: 1615646 (The Pile)

Max Activating Token Index: 448

Text #13

Max Range: 0.9791. Min Range: -0.9791

Max Act: 0.6439. Min Act: -0.0000

Data Index: 1030589 (The Pile)

Max Activating Token Index: 123

Text #14

Max Range: 0.9791. Min Range: -0.9791

Max Act: 0.6402. Min Act: -0.0000

Data Index: 384193 (The Pile)

Max Activating Token Index: 363

Text #15

Max Range: 0.9791. Min Range: -0.9791

Max Act: 0.7127. Min Act: -0.0000

Data Index: 1260532 (The Pile)

Max Activating Token Index: 168

Text #16

Max Range: 0.9791. Min Range: -0.9791

Max Act: 0.6303. Min Act: -0.0000

Data Index: 766212 (The Pile)

Max Activating Token Index: 794

Text #17

Max Range: 0.9791. Min Range: -0.9791

Max Act: 0.6059. Min Act: -0.0000

Data Index: 733714 (The Pile)

Max Activating Token Index: 96

Text #18

Max Range: 0.9791. Min Range: -0.9791

Max Act: 0.6432. Min Act: -0.0000

Data Index: 662728 (The Pile)

Max Activating Token Index: 169

Text #19

Max Range: 0.9791. Min Range: -0.9791

Max Act: 0.6052. Min Act: -0.0000

Data Index: 424777 (The Pile)

Max Activating Token Index: 145