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

Dataset: The Pile

Neuron 2745 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1227. Min Range: -0.1227

Max Act: 0.1227. Min Act: -0.0000

Data Index: 893919 (The Pile)

Max Activating Token Index: 346

Text #1

Max Range: 0.1227. Min Range: -0.1227

Max Act: 0.1157. Min Act: -0.0000

Data Index: 1588978 (The Pile)

Max Activating Token Index: 131

Text #2

Max Range: 0.1227. Min Range: -0.1227

Max Act: 0.1101. Min Act: -0.0000

Data Index: 409772 (The Pile)

Max Activating Token Index: 672

Text #3

Max Range: 0.1227. Min Range: -0.1227

Max Act: 0.1136. Min Act: -0.0000

Data Index: 1388743 (The Pile)

Max Activating Token Index: 573

Text #4

Max Range: 0.1227. Min Range: -0.1227

Max Act: 0.1106. Min Act: -0.0000

Data Index: 679690 (The Pile)

Max Activating Token Index: 570

Text #5

Max Range: 0.1227. Min Range: -0.1227

Max Act: 0.1148. Min Act: -0.0000

Data Index: 1303308 (The Pile)

Max Activating Token Index: 752

Text #6

Max Range: 0.1227. Min Range: -0.1227

Max Act: 0.1079. Min Act: -0.0000

Data Index: 964798 (The Pile)

Max Activating Token Index: 313

Text #7

Max Range: 0.1227. Min Range: -0.1227

Max Act: 0.1020. Min Act: -0.0000

Data Index: 717801 (The Pile)

Max Activating Token Index: 359

Text #8

Max Range: 0.1227. Min Range: -0.1227

Max Act: 0.0981. Min Act: -0.0000

Data Index: 1100437 (The Pile)

Max Activating Token Index: 566

Text #9

Max Range: 0.1227. Min Range: -0.1227

Max Act: 0.0999. Min Act: -0.0000

Data Index: 469961 (The Pile)

Max Activating Token Index: 862

Text #10

Max Range: 0.1227. Min Range: -0.1227

Max Act: 0.0995. Min Act: -0.0000

Data Index: 311913 (The Pile)

Max Activating Token Index: 376

Text #11

Max Range: 0.1227. Min Range: -0.1227

Max Act: 0.0950. Min Act: -0.0000

Data Index: 924229 (The Pile)

Max Activating Token Index: 604

Text #12

Max Range: 0.1227. Min Range: -0.1227

Max Act: 0.0925. Min Act: -0.0000

Data Index: 687628 (The Pile)

Max Activating Token Index: 651

Text #13

Max Range: 0.1227. Min Range: -0.1227

Max Act: 0.0924. Min Act: -0.0000

Data Index: 1381611 (The Pile)

Max Activating Token Index: 486

Text #14

Max Range: 0.1227. Min Range: -0.1227

Max Act: 0.0919. Min Act: -0.0000

Data Index: 514543 (The Pile)

Max Activating Token Index: 224

Text #15

Max Range: 0.1227. Min Range: -0.1227

Max Act: 0.0915. Min Act: -0.0000

Data Index: 353533 (The Pile)

Max Activating Token Index: 746

Text #16

Max Range: 0.1227. Min Range: -0.1227

Max Act: 0.0942. Min Act: -0.0000

Data Index: 1842050 (The Pile)

Max Activating Token Index: 78

Text #17

Max Range: 0.1227. Min Range: -0.1227

Max Act: 0.0917. Min Act: -0.0000

Data Index: 641790 (The Pile)

Max Activating Token Index: 504

Text #18

Max Range: 0.1227. Min Range: -0.1227

Max Act: 0.0918. Min Act: -0.0000

Data Index: 405051 (The Pile)

Max Activating Token Index: 454

Text #19

Max Range: 0.1227. Min Range: -0.1227

Max Act: 0.0853. Min Act: -0.0000

Data Index: 1933523 (The Pile)

Max Activating Token Index: 897