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

Dataset: The Pile

Neuron 2908 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6197. Min Range: -0.6197

Max Act: 0.6197. Min Act: -0.0000

Data Index: 882794 (The Pile)

Max Activating Token Index: 241

Text #1

Max Range: 0.6197. Min Range: -0.6197

Max Act: 0.5471. Min Act: -0.0000

Data Index: 184668 (The Pile)

Max Activating Token Index: 110

Text #2

Max Range: 0.6197. Min Range: -0.6197

Max Act: 0.5360. Min Act: -0.0000

Data Index: 1833010 (The Pile)

Max Activating Token Index: 370

Text #3

Max Range: 0.6197. Min Range: -0.6197

Max Act: 0.5391. Min Act: -0.0000

Data Index: 391700 (The Pile)

Max Activating Token Index: 185

Text #4

Max Range: 0.6197. Min Range: -0.6197

Max Act: 0.5189. Min Act: -0.0000

Data Index: 894904 (The Pile)

Max Activating Token Index: 881

Text #5

Max Range: 0.6197. Min Range: -0.6197

Max Act: 0.5130. Min Act: -0.0000

Data Index: 1823532 (The Pile)

Max Activating Token Index: 494

Text #6

Max Range: 0.6197. Min Range: -0.6197

Max Act: 0.4926. Min Act: -0.0000

Data Index: 1608072 (The Pile)

Max Activating Token Index: 305

Text #7

Max Range: 0.6197. Min Range: -0.6197

Max Act: 0.4870. Min Act: -0.0000

Data Index: 746749 (The Pile)

Max Activating Token Index: 559

Text #8

Max Range: 0.6197. Min Range: -0.6197

Max Act: 0.4788. Min Act: -0.0000

Data Index: 443372 (The Pile)

Max Activating Token Index: 936

Text #9

Max Range: 0.6197. Min Range: -0.6197

Max Act: 0.4571. Min Act: -0.0000

Data Index: 1222386 (The Pile)

Max Activating Token Index: 173

Text #10

Max Range: 0.6197. Min Range: -0.6197

Max Act: 0.4539. Min Act: -0.0000

Data Index: 1606254 (The Pile)

Max Activating Token Index: 534

Text #11

Max Range: 0.6197. Min Range: -0.6197

Max Act: 0.3888. Min Act: -0.0000

Data Index: 1397602 (The Pile)

Max Activating Token Index: 951

Text #12

Max Range: 0.6197. Min Range: -0.6197

Max Act: 0.4344. Min Act: -0.0000

Data Index: 1655252 (The Pile)

Max Activating Token Index: 120

Text #13

Max Range: 0.6197. Min Range: -0.6197

Max Act: 0.4135. Min Act: -0.0000

Data Index: 545792 (The Pile)

Max Activating Token Index: 980

Text #14

Max Range: 0.6197. Min Range: -0.6197

Max Act: 0.4169. Min Act: -0.0000

Data Index: 413014 (The Pile)

Max Activating Token Index: 66

Text #15

Max Range: 0.6197. Min Range: -0.6197

Max Act: 0.4391. Min Act: -0.0000

Data Index: 1311965 (The Pile)

Max Activating Token Index: 750

Text #16

Max Range: 0.6197. Min Range: -0.6197

Max Act: 0.4058. Min Act: -0.0000

Data Index: 221272 (The Pile)

Max Activating Token Index: 1017

Text #17

Max Range: 0.6197. Min Range: -0.6197

Max Act: 0.3850. Min Act: -0.0000

Data Index: 359907 (The Pile)

Max Activating Token Index: 235

Text #18

Max Range: 0.6197. Min Range: -0.6197

Max Act: 0.4028. Min Act: -0.0000

Data Index: 830857 (The Pile)

Max Activating Token Index: 911

Text #19

Max Range: 0.6197. Min Range: -0.6197

Max Act: 0.3957. Min Act: -0.0000

Data Index: 1166590 (The Pile)

Max Activating Token Index: 107