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

Dataset: The Pile

Neuron 4047 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: 0.9133. Min Range: -0.9133

Max Act: 0.9133. Min Act: -0.0000

Data Index: 746395 (The Pile)

Max Activating Token Index: 188

Text #1

Max Range: 0.9133. Min Range: -0.9133

Max Act: 0.8531. Min Act: -0.0000

Data Index: 1304793 (The Pile)

Max Activating Token Index: 941

Text #2

Max Range: 0.9133. Min Range: -0.9133

Max Act: 0.8427. Min Act: -0.0000

Data Index: 301010 (The Pile)

Max Activating Token Index: 739

Text #3

Max Range: 0.9133. Min Range: -0.9133

Max Act: 0.8053. Min Act: -0.0000

Data Index: 1180404 (The Pile)

Max Activating Token Index: 409

Text #4

Max Range: 0.9133. Min Range: -0.9133

Max Act: 0.7492. Min Act: -0.0000

Data Index: 745651 (The Pile)

Max Activating Token Index: 748

Text #5

Max Range: 0.9133. Min Range: -0.9133

Max Act: 0.8368. Min Act: -0.0000

Data Index: 1591155 (The Pile)

Max Activating Token Index: 183

Text #6

Max Range: 0.9133. Min Range: -0.9133

Max Act: 0.7903. Min Act: -0.0000

Data Index: 1792954 (The Pile)

Max Activating Token Index: 774

Text #7

Max Range: 0.9133. Min Range: -0.9133

Max Act: 0.8009. Min Act: -0.0000

Data Index: 1436046 (The Pile)

Max Activating Token Index: 843

Text #8

Max Range: 0.9133. Min Range: -0.9133

Max Act: 0.7906. Min Act: -0.0000

Data Index: 779640 (The Pile)

Max Activating Token Index: 137

Text #9

Max Range: 0.9133. Min Range: -0.9133

Max Act: 0.8395. Min Act: -0.0000

Data Index: 995189 (The Pile)

Max Activating Token Index: 553

Text #10

Max Range: 0.9133. Min Range: -0.9133

Max Act: 0.7866. Min Act: -0.0000

Data Index: 1195388 (The Pile)

Max Activating Token Index: 822

Text #11

Max Range: 0.9133. Min Range: -0.9133

Max Act: 0.7889. Min Act: -0.0000

Data Index: 476208 (The Pile)

Max Activating Token Index: 818

Text #12

Max Range: 0.9133. Min Range: -0.9133

Max Act: 0.7985. Min Act: -0.0000

Data Index: 449723 (The Pile)

Max Activating Token Index: 730

Text #13

Max Range: 0.9133. Min Range: -0.9133

Max Act: 0.7484. Min Act: -0.0000

Data Index: 1408039 (The Pile)

Max Activating Token Index: 759

Text #14

Max Range: 0.9133. Min Range: -0.9133

Max Act: 0.7728. Min Act: -0.0000

Data Index: 1470856 (The Pile)

Max Activating Token Index: 809

Text #15

Max Range: 0.9133. Min Range: -0.9133

Max Act: 0.7903. Min Act: -0.0000

Data Index: 589724 (The Pile)

Max Activating Token Index: 261

Text #16

Max Range: 0.9133. Min Range: -0.9133

Max Act: 0.7173. Min Act: -0.0000

Data Index: 1603320 (The Pile)

Max Activating Token Index: 521

Text #17

Max Range: 0.9133. Min Range: -0.9133

Max Act: 0.7174. Min Act: -0.0000

Data Index: 334207 (The Pile)

Max Activating Token Index: 944

Text #18

Max Range: 0.9133. Min Range: -0.9133

Max Act: 0.6872. Min Act: -0.0000

Data Index: 414243 (The Pile)

Max Activating Token Index: 35

Text #19

Max Range: 0.9133. Min Range: -0.9133

Max Act: 0.7636. Min Act: -0.0000

Data Index: 1620982 (The Pile)

Max Activating Token Index: 149