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

Dataset: The Pile

Neuron 1627 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1363. Min Range: -0.1363

Max Act: 0.1363. Min Act: -0.0000

Data Index: 972671 (The Pile)

Max Activating Token Index: 248

Text #1

Max Range: 0.1363. Min Range: -0.1363

Max Act: 0.1179. Min Act: -0.0000

Data Index: 168902 (The Pile)

Max Activating Token Index: 202

Text #2

Max Range: 0.1363. Min Range: -0.1363

Max Act: 0.1153. Min Act: -0.0000

Data Index: 189691 (The Pile)

Max Activating Token Index: 470

Text #3

Max Range: 0.1363. Min Range: -0.1363

Max Act: 0.1189. Min Act: -0.0000

Data Index: 1456806 (The Pile)

Max Activating Token Index: 563

Text #4

Max Range: 0.1363. Min Range: -0.1363

Max Act: 0.1200. Min Act: -0.0000

Data Index: 1847616 (The Pile)

Max Activating Token Index: 631

Text #5

Max Range: 0.1363. Min Range: -0.1363

Max Act: 0.1078. Min Act: -0.0000

Data Index: 1074061 (The Pile)

Max Activating Token Index: 599

Text #6

Max Range: 0.1363. Min Range: -0.1363

Max Act: 0.1156. Min Act: -0.0000

Data Index: 358764 (The Pile)

Max Activating Token Index: 312

Text #7

Max Range: 0.1363. Min Range: -0.1363

Max Act: 0.1224. Min Act: -0.0000

Data Index: 1322391 (The Pile)

Max Activating Token Index: 257

Text #8

Max Range: 0.1363. Min Range: -0.1363

Max Act: 0.1140. Min Act: -0.0000

Data Index: 589606 (The Pile)

Max Activating Token Index: 594

Text #9

Max Range: 0.1363. Min Range: -0.1363

Max Act: 0.1159. Min Act: -0.0000

Data Index: 1139000 (The Pile)

Max Activating Token Index: 955

Text #10

Max Range: 0.1363. Min Range: -0.1363

Max Act: 0.1074. Min Act: -0.0000

Data Index: 464568 (The Pile)

Max Activating Token Index: 384

Text #11

Max Range: 0.1363. Min Range: -0.1363

Max Act: 0.1027. Min Act: -0.0000

Data Index: 124094 (The Pile)

Max Activating Token Index: 629

Text #12

Max Range: 0.1363. Min Range: -0.1363

Max Act: 0.0875. Min Act: -0.0000

Data Index: 1671971 (The Pile)

Max Activating Token Index: 820

Text #13

Max Range: 0.1363. Min Range: -0.1363

Max Act: 0.0929. Min Act: -0.0000

Data Index: 1078096 (The Pile)

Max Activating Token Index: 633

Text #14

Max Range: 0.1363. Min Range: -0.1363

Max Act: 0.1120. Min Act: -0.0000

Data Index: 249466 (The Pile)

Max Activating Token Index: 958

Text #15

Max Range: 0.1363. Min Range: -0.1363

Max Act: 0.1022. Min Act: -0.0000

Data Index: 682051 (The Pile)

Max Activating Token Index: 414

Text #16

Max Range: 0.1363. Min Range: -0.1363

Max Act: 0.1014. Min Act: -0.0000

Data Index: 881654 (The Pile)

Max Activating Token Index: 446

Text #17

Max Range: 0.1363. Min Range: -0.1363

Max Act: 0.1016. Min Act: -0.0000

Data Index: 556485 (The Pile)

Max Activating Token Index: 979

Text #18

Max Range: 0.1363. Min Range: -0.1363

Max Act: 0.1043. Min Act: -0.0000

Data Index: 1493774 (The Pile)

Max Activating Token Index: 467

Text #19

Max Range: 0.1363. Min Range: -0.1363

Max Act: 0.0979. Min Act: -0.0000

Data Index: 1498789 (The Pile)

Max Activating Token Index: 676