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

Dataset: The Pile

Neuron 2494 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1371. Min Act: -0.0000

Data Index: 412882 (The Pile)

Max Activating Token Index: 740

Text #1

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1174. Min Act: -0.0000

Data Index: 198418 (The Pile)

Max Activating Token Index: 694

Text #2

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1224. Min Act: -0.0000

Data Index: 620920 (The Pile)

Max Activating Token Index: 449

Text #3

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1149. Min Act: -0.0000

Data Index: 263015 (The Pile)

Max Activating Token Index: 182

Text #4

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1154. Min Act: -0.0000

Data Index: 1990997 (The Pile)

Max Activating Token Index: 97

Text #5

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1034. Min Act: -0.0000

Data Index: 1862930 (The Pile)

Max Activating Token Index: 371

Text #6

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.0974. Min Act: -0.0000

Data Index: 1391735 (The Pile)

Max Activating Token Index: 982

Text #7

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1002. Min Act: -0.0000

Data Index: 138620 (The Pile)

Max Activating Token Index: 285

Text #8

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1057. Min Act: -0.0000

Data Index: 398989 (The Pile)

Max Activating Token Index: 593

Text #9

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.0878. Min Act: -0.0000

Data Index: 396985 (The Pile)

Max Activating Token Index: 1014

Text #10

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1079. Min Act: -0.0000

Data Index: 452677 (The Pile)

Max Activating Token Index: 294

Text #11

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.0935. Min Act: -0.0001

Data Index: 1791134 (The Pile)

Max Activating Token Index: 854

Text #12

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1078. Min Act: -0.0000

Data Index: 1042862 (The Pile)

Max Activating Token Index: 137

Text #13

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1031. Min Act: -0.0000

Data Index: 262493 (The Pile)

Max Activating Token Index: 945

Text #14

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.0962. Min Act: -0.0000

Data Index: 671026 (The Pile)

Max Activating Token Index: 579

Text #15

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.0992. Min Act: -0.0000

Data Index: 155118 (The Pile)

Max Activating Token Index: 66

Text #16

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.0988. Min Act: -0.0000

Data Index: 143482 (The Pile)

Max Activating Token Index: 921

Text #17

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1015. Min Act: -0.0000

Data Index: 275546 (The Pile)

Max Activating Token Index: 329

Text #18

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.0974. Min Act: -0.0000

Data Index: 858581 (The Pile)

Max Activating Token Index: 614

Text #19

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.0971. Min Act: -0.0000

Data Index: 1581606 (The Pile)

Max Activating Token Index: 479