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

Dataset: The Pile

Neuron 2565 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: 0.7427. Min Range: -0.7427

Max Act: 0.7281. Min Act: -0.0000

Data Index: 1816181 (The Pile)

Max Activating Token Index: 731

Text #1

Max Range: 0.7427. Min Range: -0.7427

Max Act: 0.7008. Min Act: -0.0000

Data Index: 1513743 (The Pile)

Max Activating Token Index: 455

Text #2

Max Range: 0.7427. Min Range: -0.7427

Max Act: 0.7427. Min Act: -0.0000

Data Index: 588718 (The Pile)

Max Activating Token Index: 319

Text #3

Max Range: 0.7427. Min Range: -0.7427

Max Act: 0.6422. Min Act: -0.0000

Data Index: 214887 (The Pile)

Max Activating Token Index: 287

Text #4

Max Range: 0.7427. Min Range: -0.7427

Max Act: 0.6312. Min Act: -0.0000

Data Index: 63505 (The Pile)

Max Activating Token Index: 522

Text #5

Max Range: 0.7427. Min Range: -0.7427

Max Act: 0.6708. Min Act: -0.0000

Data Index: 1258291 (The Pile)

Max Activating Token Index: 301

Text #6

Max Range: 0.7427. Min Range: -0.7427

Max Act: 0.6052. Min Act: -0.0000

Data Index: 143650 (The Pile)

Max Activating Token Index: 157

Text #7

Max Range: 0.7427. Min Range: -0.7427

Max Act: 0.6186. Min Act: -0.0000

Data Index: 1907473 (The Pile)

Max Activating Token Index: 528

Text #8

Max Range: 0.7427. Min Range: -0.7427

Max Act: 0.5998. Min Act: -0.0000

Data Index: 931450 (The Pile)

Max Activating Token Index: 169

Text #9

Max Range: 0.7427. Min Range: -0.7427

Max Act: 0.6169. Min Act: -0.0000

Data Index: 561010 (The Pile)

Max Activating Token Index: 274

Text #10

Max Range: 0.7427. Min Range: -0.7427

Max Act: 0.5911. Min Act: -0.0000

Data Index: 1995812 (The Pile)

Max Activating Token Index: 733

Text #11

Max Range: 0.7427. Min Range: -0.7427

Max Act: 0.5893. Min Act: -0.0000

Data Index: 790806 (The Pile)

Max Activating Token Index: 308

Text #12

Max Range: 0.7427. Min Range: -0.7427

Max Act: 0.6258. Min Act: -0.0000

Data Index: 946616 (The Pile)

Max Activating Token Index: 383

Text #13

Max Range: 0.7427. Min Range: -0.7427

Max Act: 0.6051. Min Act: -0.0000

Data Index: 179956 (The Pile)

Max Activating Token Index: 234

Text #14

Max Range: 0.7427. Min Range: -0.7427

Max Act: 0.6430. Min Act: -0.0000

Data Index: 2440 (The Pile)

Max Activating Token Index: 735

Text #15

Max Range: 0.7427. Min Range: -0.7427

Max Act: 0.6173. Min Act: -0.0000

Data Index: 738384 (The Pile)

Max Activating Token Index: 387

Text #16

Max Range: 0.7427. Min Range: -0.7427

Max Act: 0.5526. Min Act: -0.0000

Data Index: 186664 (The Pile)

Max Activating Token Index: 954

Text #17

Max Range: 0.7427. Min Range: -0.7427

Max Act: 0.6131. Min Act: -0.0000

Data Index: 1111062 (The Pile)

Max Activating Token Index: 247

Text #18

Max Range: 0.7427. Min Range: -0.7427

Max Act: 0.6053. Min Act: -0.0000

Data Index: 1036317 (The Pile)

Max Activating Token Index: 91

Text #19

Max Range: 0.7427. Min Range: -0.7427

Max Act: 0.6025. Min Act: -0.0000

Data Index: 553805 (The Pile)

Max Activating Token Index: 493