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

Dataset: The Pile

Neuron 701 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1501. Min Range: -0.1501

Max Act: 0.1365. Min Act: -0.0000

Data Index: 1303909 (The Pile)

Max Activating Token Index: 386

Text #1

Max Range: 0.1501. Min Range: -0.1501

Max Act: 0.1315. Min Act: -0.0000

Data Index: 1717098 (The Pile)

Max Activating Token Index: 789

Text #2

Max Range: 0.1501. Min Range: -0.1501

Max Act: 0.1256. Min Act: -0.0000

Data Index: 1446651 (The Pile)

Max Activating Token Index: 242

Text #3

Max Range: 0.1501. Min Range: -0.1501

Max Act: 0.1501. Min Act: -0.0000

Data Index: 1954603 (The Pile)

Max Activating Token Index: 474

Text #4

Max Range: 0.1501. Min Range: -0.1501

Max Act: 0.1197. Min Act: -0.0000

Data Index: 1082161 (The Pile)

Max Activating Token Index: 312

Text #5

Max Range: 0.1501. Min Range: -0.1501

Max Act: 0.1175. Min Act: -0.0000

Data Index: 1896592 (The Pile)

Max Activating Token Index: 237

Text #6

Max Range: 0.1501. Min Range: -0.1501

Max Act: 0.1160. Min Act: -0.0000

Data Index: 103533 (The Pile)

Max Activating Token Index: 64

Text #7

Max Range: 0.1501. Min Range: -0.1501

Max Act: 0.1143. Min Act: -0.0000

Data Index: 179723 (The Pile)

Max Activating Token Index: 266

Text #8

Max Range: 0.1501. Min Range: -0.1501

Max Act: 0.1143. Min Act: -0.0000

Data Index: 944062 (The Pile)

Max Activating Token Index: 439

Text #9

Max Range: 0.1501. Min Range: -0.1501

Max Act: 0.1107. Min Act: -0.0000

Data Index: 1888087 (The Pile)

Max Activating Token Index: 328

Text #10

Max Range: 0.1501. Min Range: -0.1501

Max Act: 0.0968. Min Act: -0.0000

Data Index: 1482279 (The Pile)

Max Activating Token Index: 661

Text #11

Max Range: 0.1501. Min Range: -0.1501

Max Act: 0.1024. Min Act: -0.0000

Data Index: 1020691 (The Pile)

Max Activating Token Index: 894

Text #12

Max Range: 0.1501. Min Range: -0.1501

Max Act: 0.1057. Min Act: -0.0000

Data Index: 1326159 (The Pile)

Max Activating Token Index: 400

Text #13

Max Range: 0.1501. Min Range: -0.1501

Max Act: 0.1057. Min Act: -0.0000

Data Index: 1665552 (The Pile)

Max Activating Token Index: 819

Text #14

Max Range: 0.1501. Min Range: -0.1501

Max Act: 0.0969. Min Act: -0.0000

Data Index: 217571 (The Pile)

Max Activating Token Index: 642

Text #15

Max Range: 0.1501. Min Range: -0.1501

Max Act: 0.1086. Min Act: -0.0000

Data Index: 1724288 (The Pile)

Max Activating Token Index: 807

Text #16

Max Range: 0.1501. Min Range: -0.1501

Max Act: 0.0983. Min Act: -0.0000

Data Index: 1027491 (The Pile)

Max Activating Token Index: 159

Text #17

Max Range: 0.1501. Min Range: -0.1501

Max Act: 0.1047. Min Act: -0.0000

Data Index: 195676 (The Pile)

Max Activating Token Index: 299

Text #18

Max Range: 0.1501. Min Range: -0.1501

Max Act: 0.1084. Min Act: -0.0000

Data Index: 1741639 (The Pile)

Max Activating Token Index: 629

Text #19

Max Range: 0.1501. Min Range: -0.1501

Max Act: 0.1029. Min Act: -0.0000

Data Index: 905675 (The Pile)

Max Activating Token Index: 788