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

Dataset: The Pile

Neuron 1387 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: 1.3864. Min Range: -1.3864

Max Act: 1.3864. Min Act: -0.0000

Data Index: 215663 (The Pile)

Max Activating Token Index: 847

Text #1

Max Range: 1.3864. Min Range: -1.3864

Max Act: 1.2975. Min Act: -0.0000

Data Index: 1459145 (The Pile)

Max Activating Token Index: 261

Text #2

Max Range: 1.3864. Min Range: -1.3864

Max Act: 1.2990. Min Act: -0.0000

Data Index: 38026 (The Pile)

Max Activating Token Index: 14

Text #3

Max Range: 1.3864. Min Range: -1.3864

Max Act: 1.2697. Min Act: -0.0000

Data Index: 1079176 (The Pile)

Max Activating Token Index: 805

Text #4

Max Range: 1.3864. Min Range: -1.3864

Max Act: 1.3371. Min Act: -0.0000

Data Index: 1371513 (The Pile)

Max Activating Token Index: 791

Text #5

Max Range: 1.3864. Min Range: -1.3864

Max Act: 1.2403. Min Act: -0.0000

Data Index: 1125187 (The Pile)

Max Activating Token Index: 24

Text #6

Max Range: 1.3864. Min Range: -1.3864

Max Act: 1.2243. Min Act: -0.0000

Data Index: 1719340 (The Pile)

Max Activating Token Index: 1007

Text #7

Max Range: 1.3864. Min Range: -1.3864

Max Act: 1.1622. Min Act: -0.0000

Data Index: 995176 (The Pile)

Max Activating Token Index: 937

Text #8

Max Range: 1.3864. Min Range: -1.3864

Max Act: 1.1948. Min Act: -0.0000

Data Index: 1217930 (The Pile)

Max Activating Token Index: 953

Text #9

Max Range: 1.3864. Min Range: -1.3864

Max Act: 1.0988. Min Act: -0.0000

Data Index: 1632123 (The Pile)

Max Activating Token Index: 977

Text #10

Max Range: 1.3864. Min Range: -1.3864

Max Act: 1.2213. Min Act: -0.0000

Data Index: 1961456 (The Pile)

Max Activating Token Index: 179

Text #11

Max Range: 1.3864. Min Range: -1.3864

Max Act: 1.1455. Min Act: -0.0000

Data Index: 583141 (The Pile)

Max Activating Token Index: 954

Text #12

Max Range: 1.3864. Min Range: -1.3864

Max Act: 1.1392. Min Act: -0.0000

Data Index: 1721637 (The Pile)

Max Activating Token Index: 310

Text #13

Max Range: 1.3864. Min Range: -1.3864

Max Act: 1.0548. Min Act: -0.0000

Data Index: 1188505 (The Pile)

Max Activating Token Index: 1023

Text #14

Max Range: 1.3864. Min Range: -1.3864

Max Act: 1.0981. Min Act: -0.0000

Data Index: 617354 (The Pile)

Max Activating Token Index: 649

Text #15

Max Range: 1.3864. Min Range: -1.3864

Max Act: 1.1239. Min Act: -0.0000

Data Index: 465956 (The Pile)

Max Activating Token Index: 989

Text #16

Max Range: 1.3864. Min Range: -1.3864

Max Act: 1.0850. Min Act: -0.0000

Data Index: 572948 (The Pile)

Max Activating Token Index: 1018

Text #17

Max Range: 1.3864. Min Range: -1.3864

Max Act: 1.1380. Min Act: -0.0000

Data Index: 1733036 (The Pile)

Max Activating Token Index: 591

Text #18

Max Range: 1.3864. Min Range: -1.3864

Max Act: 1.1008. Min Act: -0.0000

Data Index: 1233128 (The Pile)

Max Activating Token Index: 876

Text #19

Max Range: 1.3864. Min Range: -1.3864

Max Act: 1.1035. Min Act: -0.0000

Data Index: 1057530 (The Pile)

Max Activating Token Index: 580