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

Dataset: The Pile

Neuron 3891 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: 0.5321. Min Range: -0.5321

Max Act: 0.5321. Min Act: -0.0000

Data Index: 878888 (The Pile)

Max Activating Token Index: 21

Text #1

Max Range: 0.5321. Min Range: -0.5321

Max Act: 0.4718. Min Act: -0.0000

Data Index: 802783 (The Pile)

Max Activating Token Index: 22

Text #2

Max Range: 0.5321. Min Range: -0.5321

Max Act: 0.5072. Min Act: -0.0000

Data Index: 1048511 (The Pile)

Max Activating Token Index: 308

Text #3

Max Range: 0.5321. Min Range: -0.5321

Max Act: 0.4788. Min Act: -0.0000

Data Index: 1677481 (The Pile)

Max Activating Token Index: 553

Text #4

Max Range: 0.5321. Min Range: -0.5321

Max Act: 0.4893. Min Act: -0.0000

Data Index: 570954 (The Pile)

Max Activating Token Index: 803

Text #5

Max Range: 0.5321. Min Range: -0.5321

Max Act: 0.4715. Min Act: -0.0000

Data Index: 1904992 (The Pile)

Max Activating Token Index: 957

Text #6

Max Range: 0.5321. Min Range: -0.5321

Max Act: 0.4171. Min Act: -0.0000

Data Index: 1146098 (The Pile)

Max Activating Token Index: 306

Text #7

Max Range: 0.5321. Min Range: -0.5321

Max Act: 0.3910. Min Act: -0.0000

Data Index: 1748726 (The Pile)

Max Activating Token Index: 895

Text #8

Max Range: 0.5321. Min Range: -0.5321

Max Act: 0.4378. Min Act: -0.0000

Data Index: 126151 (The Pile)

Max Activating Token Index: 51

Text #9

Max Range: 0.5321. Min Range: -0.5321

Max Act: 0.3910. Min Act: -0.0000

Data Index: 209723 (The Pile)

Max Activating Token Index: 815

Text #10

Max Range: 0.5321. Min Range: -0.5321

Max Act: 0.4235. Min Act: -0.0000

Data Index: 1097331 (The Pile)

Max Activating Token Index: 530

Text #11

Max Range: 0.5321. Min Range: -0.5321

Max Act: 0.4241. Min Act: -0.0000

Data Index: 1770683 (The Pile)

Max Activating Token Index: 602

Text #12

Max Range: 0.5321. Min Range: -0.5321

Max Act: 0.4380. Min Act: -0.0000

Data Index: 1954313 (The Pile)

Max Activating Token Index: 115

Text #13

Max Range: 0.5321. Min Range: -0.5321

Max Act: 0.4028. Min Act: -0.0000

Data Index: 1556399 (The Pile)

Max Activating Token Index: 933

Text #14

Max Range: 0.5321. Min Range: -0.5321

Max Act: 0.4460. Min Act: -0.0000

Data Index: 624385 (The Pile)

Max Activating Token Index: 416

Text #15

Max Range: 0.5321. Min Range: -0.5321

Max Act: 0.4658. Min Act: -0.0000

Data Index: 1760191 (The Pile)

Max Activating Token Index: 822

Text #16

Max Range: 0.5321. Min Range: -0.5321

Max Act: 0.4360. Min Act: -0.0000

Data Index: 181393 (The Pile)

Max Activating Token Index: 858

Text #17

Max Range: 0.5321. Min Range: -0.5321

Max Act: 0.3591. Min Act: -0.0000

Data Index: 1035961 (The Pile)

Max Activating Token Index: 287

Text #18

Max Range: 0.5321. Min Range: -0.5321

Max Act: 0.4185. Min Act: -0.0000

Data Index: 1791087 (The Pile)

Max Activating Token Index: 963

Text #19

Max Range: 0.5321. Min Range: -0.5321

Max Act: 0.4194. Min Act: -0.0000

Data Index: 847626 (The Pile)

Max Activating Token Index: 1023