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

Dataset: The Pile

Neuron 2904 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7983. Min Range: -0.7983

Max Act: 0.7983. Min Act: 0.0000

Data Index: 245988 (The Pile)

Max Activating Token Index: 120

Text #1

Max Range: 0.7983. Min Range: -0.7983

Max Act: 0.6932. Min Act: -0.0000

Data Index: 1549625 (The Pile)

Max Activating Token Index: 375

Text #2

Max Range: 0.7983. Min Range: -0.7983

Max Act: 0.6711. Min Act: 0.0000

Data Index: 1160467 (The Pile)

Max Activating Token Index: 647

Text #3

Max Range: 0.7983. Min Range: -0.7983

Max Act: 0.6051. Min Act: 0.0004

Data Index: 173061 (The Pile)

Max Activating Token Index: 179

Text #4

Max Range: 0.7983. Min Range: -0.7983

Max Act: 0.6248. Min Act: 0.0000

Data Index: 782389 (The Pile)

Max Activating Token Index: 243

Text #5

Max Range: 0.7983. Min Range: -0.7983

Max Act: 0.5869. Min Act: -0.0000

Data Index: 796400 (The Pile)

Max Activating Token Index: 215

Text #6

Max Range: 0.7983. Min Range: -0.7983

Max Act: 0.6041. Min Act: -0.0000

Data Index: 1921130 (The Pile)

Max Activating Token Index: 700

Text #7

Max Range: 0.7983. Min Range: -0.7983

Max Act: 0.6324. Min Act: -0.0000

Data Index: 1101690 (The Pile)

Max Activating Token Index: 370

Text #8

Max Range: 0.7983. Min Range: -0.7983

Max Act: 0.5739. Min Act: -0.0000

Data Index: 662762 (The Pile)

Max Activating Token Index: 386

Text #9

Max Range: 0.7983. Min Range: -0.7983

Max Act: 0.6024. Min Act: -0.0000

Data Index: 1385303 (The Pile)

Max Activating Token Index: 156

Text #10

Max Range: 0.7983. Min Range: -0.7983

Max Act: 0.5769. Min Act: -0.0000

Data Index: 1843943 (The Pile)

Max Activating Token Index: 808

Text #11

Max Range: 0.7983. Min Range: -0.7983

Max Act: 0.5577. Min Act: -0.0000

Data Index: 301786 (The Pile)

Max Activating Token Index: 489

Text #12

Max Range: 0.7983. Min Range: -0.7983

Max Act: 0.5688. Min Act: -0.0000

Data Index: 430043 (The Pile)

Max Activating Token Index: 566

Text #13

Max Range: 0.7983. Min Range: -0.7983

Max Act: 0.5773. Min Act: -0.0000

Data Index: 219282 (The Pile)

Max Activating Token Index: 914

Text #14

Max Range: 0.7983. Min Range: -0.7983

Max Act: 0.5551. Min Act: -0.0000

Data Index: 130109 (The Pile)

Max Activating Token Index: 270

Text #15

Max Range: 0.7983. Min Range: -0.7983

Max Act: 0.5448. Min Act: 0.0002

Data Index: 1494788 (The Pile)

Max Activating Token Index: 189

Text #16

Max Range: 0.7983. Min Range: -0.7983

Max Act: 0.5647. Min Act: -0.0000

Data Index: 719259 (The Pile)

Max Activating Token Index: 344

Text #17

Max Range: 0.7983. Min Range: -0.7983

Max Act: 0.5172. Min Act: -0.0000

Data Index: 129987 (The Pile)

Max Activating Token Index: 300

Text #18

Max Range: 0.7983. Min Range: -0.7983

Max Act: 0.5662. Min Act: 0.0000

Data Index: 535963 (The Pile)

Max Activating Token Index: 40

Text #19

Max Range: 0.7983. Min Range: -0.7983

Max Act: 0.5433. Min Act: -0.0000

Data Index: 1504445 (The Pile)

Max Activating Token Index: 108