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

Dataset: The Pile

Neuron 1568 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9910. Min Range: -0.9910

Max Act: 0.9910. Min Act: -0.0000

Data Index: 1968668 (The Pile)

Max Activating Token Index: 287

Text #1

Max Range: 0.9910. Min Range: -0.9910

Max Act: 0.9798. Min Act: -0.0000

Data Index: 201543 (The Pile)

Max Activating Token Index: 729

Text #2

Max Range: 0.9910. Min Range: -0.9910

Max Act: 0.9669. Min Act: -0.0000

Data Index: 1399694 (The Pile)

Max Activating Token Index: 657

Text #3

Max Range: 0.9910. Min Range: -0.9910

Max Act: 0.9112. Min Act: -0.0000

Data Index: 246206 (The Pile)

Max Activating Token Index: 35

Text #4

Max Range: 0.9910. Min Range: -0.9910

Max Act: 0.8927. Min Act: -0.0000

Data Index: 1032570 (The Pile)

Max Activating Token Index: 1003

Text #5

Max Range: 0.9910. Min Range: -0.9910

Max Act: 0.8637. Min Act: -0.0000

Data Index: 1524339 (The Pile)

Max Activating Token Index: 257

Text #6

Max Range: 0.9910. Min Range: -0.9910

Max Act: 0.9015. Min Act: -0.0000

Data Index: 431074 (The Pile)

Max Activating Token Index: 807

Text #7

Max Range: 0.9910. Min Range: -0.9910

Max Act: 0.8595. Min Act: -0.0000

Data Index: 876006 (The Pile)

Max Activating Token Index: 135

Text #8

Max Range: 0.9910. Min Range: -0.9910

Max Act: 0.8611. Min Act: -0.0000

Data Index: 94824 (The Pile)

Max Activating Token Index: 932

Text #9

Max Range: 0.9910. Min Range: -0.9910

Max Act: 0.8302. Min Act: -0.0000

Data Index: 1420639 (The Pile)

Max Activating Token Index: 703

Text #10

Max Range: 0.9910. Min Range: -0.9910

Max Act: 0.7755. Min Act: -0.0000

Data Index: 789843 (The Pile)

Max Activating Token Index: 595

Text #11

Max Range: 0.9910. Min Range: -0.9910

Max Act: 0.8490. Min Act: -0.0000

Data Index: 1072484 (The Pile)

Max Activating Token Index: 288

Text #12

Max Range: 0.9910. Min Range: -0.9910

Max Act: 0.8168. Min Act: -0.0000

Data Index: 996246 (The Pile)

Max Activating Token Index: 156

Text #13

Max Range: 0.9910. Min Range: -0.9910

Max Act: 0.7835. Min Act: -0.0000

Data Index: 113845 (The Pile)

Max Activating Token Index: 341

Text #14

Max Range: 0.9910. Min Range: -0.9910

Max Act: 0.8365. Min Act: -0.0000

Data Index: 109874 (The Pile)

Max Activating Token Index: 205

Text #15

Max Range: 0.9910. Min Range: -0.9910

Max Act: 0.8555. Min Act: -0.0000

Data Index: 406860 (The Pile)

Max Activating Token Index: 664

Text #16

Max Range: 0.9910. Min Range: -0.9910

Max Act: 0.8337. Min Act: 0.0000

Data Index: 1757532 (The Pile)

Max Activating Token Index: 820

Text #17

Max Range: 0.9910. Min Range: -0.9910

Max Act: 0.8303. Min Act: -0.0000

Data Index: 1306047 (The Pile)

Max Activating Token Index: 195

Text #18

Max Range: 0.9910. Min Range: -0.9910

Max Act: 0.8062. Min Act: -0.0000

Data Index: 893722 (The Pile)

Max Activating Token Index: 511

Text #19

Max Range: 0.9910. Min Range: -0.9910

Max Act: 0.8348. Min Act: 0.0000

Data Index: 1116484 (The Pile)

Max Activating Token Index: 1018