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

Dataset: The Pile

Neuron 3426 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: 0.7133. Min Range: -0.7133

Max Act: 0.6884. Min Act: -0.0000

Data Index: 458906 (The Pile)

Max Activating Token Index: 995

Text #1

Max Range: 0.7133. Min Range: -0.7133

Max Act: 0.6247. Min Act: -0.0000

Data Index: 247213 (The Pile)

Max Activating Token Index: 882

Text #2

Max Range: 0.7133. Min Range: -0.7133

Max Act: 0.6114. Min Act: -0.0000

Data Index: 195481 (The Pile)

Max Activating Token Index: 111

Text #3

Max Range: 0.7133. Min Range: -0.7133

Max Act: 0.6437. Min Act: -0.0000

Data Index: 151857 (The Pile)

Max Activating Token Index: 127

Text #4

Max Range: 0.7133. Min Range: -0.7133

Max Act: 0.7133. Min Act: -0.0000

Data Index: 192505 (The Pile)

Max Activating Token Index: 554

Text #5

Max Range: 0.7133. Min Range: -0.7133

Max Act: 0.6184. Min Act: -0.0000

Data Index: 960593 (The Pile)

Max Activating Token Index: 170

Text #6

Max Range: 0.7133. Min Range: -0.7133

Max Act: 0.6233. Min Act: -0.0000

Data Index: 22896 (The Pile)

Max Activating Token Index: 166

Text #7

Max Range: 0.7133. Min Range: -0.7133

Max Act: 0.5617. Min Act: -0.0000

Data Index: 672984 (The Pile)

Max Activating Token Index: 786

Text #8

Max Range: 0.7133. Min Range: -0.7133

Max Act: 0.5512. Min Act: -0.0000

Data Index: 449173 (The Pile)

Max Activating Token Index: 1011

Text #9

Max Range: 0.7133. Min Range: -0.7133

Max Act: 0.5688. Min Act: -0.0000

Data Index: 1256109 (The Pile)

Max Activating Token Index: 391

Text #10

Max Range: 0.7133. Min Range: -0.7133

Max Act: 0.6055. Min Act: -0.0000

Data Index: 1001539 (The Pile)

Max Activating Token Index: 726

Text #11

Max Range: 0.7133. Min Range: -0.7133

Max Act: 0.5635. Min Act: -0.0000

Data Index: 778609 (The Pile)

Max Activating Token Index: 555

Text #12

Max Range: 0.7133. Min Range: -0.7133

Max Act: 0.5983. Min Act: -0.0000

Data Index: 1365076 (The Pile)

Max Activating Token Index: 394

Text #13

Max Range: 0.7133. Min Range: -0.7133

Max Act: 0.5802. Min Act: -0.0000

Data Index: 379886 (The Pile)

Max Activating Token Index: 391

Text #14

Max Range: 0.7133. Min Range: -0.7133

Max Act: 0.5150. Min Act: -0.0000

Data Index: 894377 (The Pile)

Max Activating Token Index: 567

Text #15

Max Range: 0.7133. Min Range: -0.7133

Max Act: 0.5376. Min Act: -0.0000

Data Index: 1066627 (The Pile)

Max Activating Token Index: 942

Text #16

Max Range: 0.7133. Min Range: -0.7133

Max Act: 0.5389. Min Act: -0.0000

Data Index: 317529 (The Pile)

Max Activating Token Index: 262

Text #17

Max Range: 0.7133. Min Range: -0.7133

Max Act: 0.5202. Min Act: -0.0000

Data Index: 347538 (The Pile)

Max Activating Token Index: 508

Text #18

Max Range: 0.7133. Min Range: -0.7133

Max Act: 0.5180. Min Act: -0.0000

Data Index: 1843346 (The Pile)

Max Activating Token Index: 326

Text #19

Max Range: 0.7133. Min Range: -0.7133

Max Act: 0.4986. Min Act: -0.0000

Data Index: 594122 (The Pile)

Max Activating Token Index: 1005