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

Dataset: The Pile

Neuron 3768 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: 0.4991. Min Range: -0.4991

Max Act: 0.4757. Min Act: -0.0000

Data Index: 933619 (The Pile)

Max Activating Token Index: 934

Text #1

Max Range: 0.4991. Min Range: -0.4991

Max Act: 0.4973. Min Act: -0.0000

Data Index: 1548378 (The Pile)

Max Activating Token Index: 282

Text #2

Max Range: 0.4991. Min Range: -0.4991

Max Act: 0.4927. Min Act: -0.0000

Data Index: 43501 (The Pile)

Max Activating Token Index: 11

Text #3

Max Range: 0.4991. Min Range: -0.4991

Max Act: 0.4991. Min Act: -0.0000

Data Index: 1595124 (The Pile)

Max Activating Token Index: 966

Text #4

Max Range: 0.4991. Min Range: -0.4991

Max Act: 0.4293. Min Act: -0.0000

Data Index: 926145 (The Pile)

Max Activating Token Index: 160

Text #5

Max Range: 0.4991. Min Range: -0.4991

Max Act: 0.4510. Min Act: -0.0000

Data Index: 1596216 (The Pile)

Max Activating Token Index: 819

Text #6

Max Range: 0.4991. Min Range: -0.4991

Max Act: 0.4257. Min Act: -0.0000

Data Index: 1915884 (The Pile)

Max Activating Token Index: 606

Text #7

Max Range: 0.4991. Min Range: -0.4991

Max Act: 0.4347. Min Act: -0.0000

Data Index: 1533180 (The Pile)

Max Activating Token Index: 321

Text #8

Max Range: 0.4991. Min Range: -0.4991

Max Act: 0.4465. Min Act: -0.0000

Data Index: 1668667 (The Pile)

Max Activating Token Index: 84

Text #9

Max Range: 0.4991. Min Range: -0.4991

Max Act: 0.3991. Min Act: -0.0000

Data Index: 1572462 (The Pile)

Max Activating Token Index: 993

Text #10

Max Range: 0.4991. Min Range: -0.4991

Max Act: 0.4328. Min Act: -0.0000

Data Index: 360787 (The Pile)

Max Activating Token Index: 447

Text #11

Max Range: 0.4991. Min Range: -0.4991

Max Act: 0.4040. Min Act: -0.0000

Data Index: 346078 (The Pile)

Max Activating Token Index: 16

Text #12

Max Range: 0.4991. Min Range: -0.4991

Max Act: 0.4405. Min Act: -0.0000

Data Index: 1186805 (The Pile)

Max Activating Token Index: 246

Text #13

Max Range: 0.4991. Min Range: -0.4991

Max Act: 0.3984. Min Act: -0.0000

Data Index: 1328161 (The Pile)

Max Activating Token Index: 528

Text #14

Max Range: 0.4991. Min Range: -0.4991

Max Act: 0.4000. Min Act: -0.0000

Data Index: 39745 (The Pile)

Max Activating Token Index: 189

Text #15

Max Range: 0.4991. Min Range: -0.4991

Max Act: 0.3843. Min Act: -0.0000

Data Index: 438432 (The Pile)

Max Activating Token Index: 828

Text #16

Max Range: 0.4991. Min Range: -0.4991

Max Act: 0.4099. Min Act: -0.0000

Data Index: 1843276 (The Pile)

Max Activating Token Index: 170

Text #17

Max Range: 0.4991. Min Range: -0.4991

Max Act: 0.4060. Min Act: -0.0000

Data Index: 175815 (The Pile)

Max Activating Token Index: 456

Text #18

Max Range: 0.4991. Min Range: -0.4991

Max Act: 0.4050. Min Act: -0.0000

Data Index: 1986821 (The Pile)

Max Activating Token Index: 169

Text #19

Max Range: 0.4991. Min Range: -0.4991

Max Act: 0.4066. Min Act: -0.0000

Data Index: 950233 (The Pile)

Max Activating Token Index: 455