Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 3463 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.2630. Min Range: -1.2630

Max Act: 1.2630. Min Act: -0.0000

Data Index: 296182 (The Pile)

Max Activating Token Index: 335

Text #1

Max Range: 1.2630. Min Range: -1.2630

Max Act: 1.1179. Min Act: -0.0000

Data Index: 562259 (The Pile)

Max Activating Token Index: 194

Text #2

Max Range: 1.2630. Min Range: -1.2630

Max Act: 0.8831. Min Act: -0.0000

Data Index: 888794 (The Pile)

Max Activating Token Index: 838

Text #3

Max Range: 1.2630. Min Range: -1.2630

Max Act: 1.0687. Min Act: -0.0000

Data Index: 1020887 (The Pile)

Max Activating Token Index: 788

Text #4

Max Range: 1.2630. Min Range: -1.2630

Max Act: 0.9477. Min Act: -0.0000

Data Index: 112071 (The Pile)

Max Activating Token Index: 227

Text #5

Max Range: 1.2630. Min Range: -1.2630

Max Act: 1.0157. Min Act: -0.0000

Data Index: 766165 (The Pile)

Max Activating Token Index: 718

Text #6

Max Range: 1.2630. Min Range: -1.2630

Max Act: 1.1010. Min Act: -0.0000

Data Index: 310029 (The Pile)

Max Activating Token Index: 665

Text #7

Max Range: 1.2630. Min Range: -1.2630

Max Act: 0.8956. Min Act: -0.0000

Data Index: 279445 (The Pile)

Max Activating Token Index: 262

Text #8

Max Range: 1.2630. Min Range: -1.2630

Max Act: 0.8285. Min Act: -0.0000

Data Index: 1761302 (The Pile)

Max Activating Token Index: 754

Text #9

Max Range: 1.2630. Min Range: -1.2630

Max Act: 0.8186. Min Act: -0.0000

Data Index: 1283642 (The Pile)

Max Activating Token Index: 185

Text #10

Max Range: 1.2630. Min Range: -1.2630

Max Act: 0.8575. Min Act: -0.0000

Data Index: 417005 (The Pile)

Max Activating Token Index: 893

Text #11

Max Range: 1.2630. Min Range: -1.2630

Max Act: 0.9109. Min Act: -0.0000

Data Index: 1701792 (The Pile)

Max Activating Token Index: 528

Text #12

Max Range: 1.2630. Min Range: -1.2630

Max Act: 0.7436. Min Act: -0.0000

Data Index: 505363 (The Pile)

Max Activating Token Index: 471

Text #13

Max Range: 1.2630. Min Range: -1.2630

Max Act: 0.7796. Min Act: -0.0000

Data Index: 178613 (The Pile)

Max Activating Token Index: 894

Text #14

Max Range: 1.2630. Min Range: -1.2630

Max Act: 0.7120. Min Act: -0.0000

Data Index: 1944012 (The Pile)

Max Activating Token Index: 664

Text #15

Max Range: 1.2630. Min Range: -1.2630

Max Act: 0.7318. Min Act: -0.0000

Data Index: 172996 (The Pile)

Max Activating Token Index: 804

Text #16

Max Range: 1.2630. Min Range: -1.2630

Max Act: 0.6467. Min Act: -0.0000

Data Index: 269501 (The Pile)

Max Activating Token Index: 765

Text #17

Max Range: 1.2630. Min Range: -1.2630

Max Act: 0.7281. Min Act: -0.0000

Data Index: 1625522 (The Pile)

Max Activating Token Index: 917

Text #18

Max Range: 1.2630. Min Range: -1.2630

Max Act: 0.7833. Min Act: -0.0000

Data Index: 1492180 (The Pile)

Max Activating Token Index: 539

Text #19

Max Range: 1.2630. Min Range: -1.2630

Max Act: 0.7124. Min Act: -0.0000

Data Index: 1316665 (The Pile)

Max Activating Token Index: 308