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

Dataset: The Pile

Neuron 1017 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7308. Min Range: -0.7308

Max Act: 0.7308. Min Act: -0.0000

Data Index: 1748376 (The Pile)

Max Activating Token Index: 309

Text #1

Max Range: 0.7308. Min Range: -0.7308

Max Act: 0.7008. Min Act: -0.0000

Data Index: 452107 (The Pile)

Max Activating Token Index: 940

Text #2

Max Range: 0.7308. Min Range: -0.7308

Max Act: 0.6169. Min Act: -0.0000

Data Index: 1223114 (The Pile)

Max Activating Token Index: 703

Text #3

Max Range: 0.7308. Min Range: -0.7308

Max Act: 0.6013. Min Act: -0.0000

Data Index: 771145 (The Pile)

Max Activating Token Index: 10

Text #4

Max Range: 0.7308. Min Range: -0.7308

Max Act: 0.5626. Min Act: -0.0000

Data Index: 1174739 (The Pile)

Max Activating Token Index: 407

Text #5

Max Range: 0.7308. Min Range: -0.7308

Max Act: 0.5904. Min Act: -0.0000

Data Index: 812930 (The Pile)

Max Activating Token Index: 598

Text #6

Max Range: 0.7308. Min Range: -0.7308

Max Act: 0.5687. Min Act: -0.0000

Data Index: 123920 (The Pile)

Max Activating Token Index: 221

Text #7

Max Range: 0.7308. Min Range: -0.7308

Max Act: 0.5759. Min Act: -0.0000

Data Index: 268789 (The Pile)

Max Activating Token Index: 151

Text #8

Max Range: 0.7308. Min Range: -0.7308

Max Act: 0.5495. Min Act: -0.0000

Data Index: 224803 (The Pile)

Max Activating Token Index: 175

Text #9

Max Range: 0.7308. Min Range: -0.7308

Max Act: 0.5314. Min Act: -0.0000

Data Index: 302045 (The Pile)

Max Activating Token Index: 450

Text #10

Max Range: 0.7308. Min Range: -0.7308

Max Act: 0.5294. Min Act: -0.0000

Data Index: 1261920 (The Pile)

Max Activating Token Index: 521

Text #11

Max Range: 0.7308. Min Range: -0.7308

Max Act: 0.5373. Min Act: -0.0000

Data Index: 714291 (The Pile)

Max Activating Token Index: 794

Text #12

Max Range: 0.7308. Min Range: -0.7308

Max Act: 0.5366. Min Act: -0.0000

Data Index: 698853 (The Pile)

Max Activating Token Index: 713

Text #13

Max Range: 0.7308. Min Range: -0.7308

Max Act: 0.5032. Min Act: -0.0000

Data Index: 1851328 (The Pile)

Max Activating Token Index: 101

Text #14

Max Range: 0.7308. Min Range: -0.7308

Max Act: 0.5167. Min Act: -0.0000

Data Index: 235505 (The Pile)

Max Activating Token Index: 664

Text #15

Max Range: 0.7308. Min Range: -0.7308

Max Act: 0.5018. Min Act: -0.0000

Data Index: 1935668 (The Pile)

Max Activating Token Index: 533

Text #16

Max Range: 0.7308. Min Range: -0.7308

Max Act: 0.5311. Min Act: -0.0000

Data Index: 1646882 (The Pile)

Max Activating Token Index: 740

Text #17

Max Range: 0.7308. Min Range: -0.7308

Max Act: 0.4956. Min Act: -0.0000

Data Index: 1047305 (The Pile)

Max Activating Token Index: 697

Text #18

Max Range: 0.7308. Min Range: -0.7308

Max Act: 0.5464. Min Act: -0.0000

Data Index: 1444031 (The Pile)

Max Activating Token Index: 589

Text #19

Max Range: 0.7308. Min Range: -0.7308

Max Act: 0.5253. Min Act: -0.0000

Data Index: 1659915 (The Pile)

Max Activating Token Index: 506