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

Dataset: The Pile

Neuron 4053 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: 0.6083. Min Range: -0.6083

Max Act: 0.6083. Min Act: -0.0000

Data Index: 670128 (The Pile)

Max Activating Token Index: 527

Text #1

Max Range: 0.6083. Min Range: -0.6083

Max Act: 0.5362. Min Act: -0.0000

Data Index: 611526 (The Pile)

Max Activating Token Index: 918

Text #2

Max Range: 0.6083. Min Range: -0.6083

Max Act: 0.5964. Min Act: -0.0000

Data Index: 694522 (The Pile)

Max Activating Token Index: 296

Text #3

Max Range: 0.6083. Min Range: -0.6083

Max Act: 0.5729. Min Act: -0.0000

Data Index: 1939451 (The Pile)

Max Activating Token Index: 27

Text #4

Max Range: 0.6083. Min Range: -0.6083

Max Act: 0.4236. Min Act: -0.0000

Data Index: 320598 (The Pile)

Max Activating Token Index: 783

Text #5

Max Range: 0.6083. Min Range: -0.6083

Max Act: 0.4874. Min Act: -0.0000

Data Index: 713469 (The Pile)

Max Activating Token Index: 150

Text #6

Max Range: 0.6083. Min Range: -0.6083

Max Act: 0.4738. Min Act: -0.0000

Data Index: 1175971 (The Pile)

Max Activating Token Index: 431

Text #7

Max Range: 0.6083. Min Range: -0.6083

Max Act: 0.4648. Min Act: -0.0000

Data Index: 346718 (The Pile)

Max Activating Token Index: 308

Text #8

Max Range: 0.6083. Min Range: -0.6083

Max Act: 0.4054. Min Act: -0.0000

Data Index: 361823 (The Pile)

Max Activating Token Index: 987

Text #9

Max Range: 0.6083. Min Range: -0.6083

Max Act: 0.4590. Min Act: -0.0000

Data Index: 211393 (The Pile)

Max Activating Token Index: 364

Text #10

Max Range: 0.6083. Min Range: -0.6083

Max Act: 0.4286. Min Act: -0.0000

Data Index: 869824 (The Pile)

Max Activating Token Index: 307

Text #11

Max Range: 0.6083. Min Range: -0.6083

Max Act: 0.4107. Min Act: -0.0000

Data Index: 1200293 (The Pile)

Max Activating Token Index: 628

Text #12

Max Range: 0.6083. Min Range: -0.6083

Max Act: 0.4202. Min Act: -0.0000

Data Index: 1892791 (The Pile)

Max Activating Token Index: 805

Text #13

Max Range: 0.6083. Min Range: -0.6083

Max Act: 0.4729. Min Act: -0.0000

Data Index: 215698 (The Pile)

Max Activating Token Index: 757

Text #14

Max Range: 0.6083. Min Range: -0.6083

Max Act: 0.3840. Min Act: -0.0000

Data Index: 1533308 (The Pile)

Max Activating Token Index: 933

Text #15

Max Range: 0.6083. Min Range: -0.6083

Max Act: 0.3390. Min Act: -0.0000

Data Index: 128314 (The Pile)

Max Activating Token Index: 382

Text #16

Max Range: 0.6083. Min Range: -0.6083

Max Act: 0.4583. Min Act: -0.0000

Data Index: 661339 (The Pile)

Max Activating Token Index: 566

Text #17

Max Range: 0.6083. Min Range: -0.6083

Max Act: 0.4069. Min Act: -0.0000

Data Index: 1463296 (The Pile)

Max Activating Token Index: 705

Text #18

Max Range: 0.6083. Min Range: -0.6083

Max Act: 0.3766. Min Act: -0.0000

Data Index: 1802764 (The Pile)

Max Activating Token Index: 703

Text #19

Max Range: 0.6083. Min Range: -0.6083

Max Act: 0.4378. Min Act: -0.0000

Data Index: 1094051 (The Pile)

Max Activating Token Index: 729