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

Dataset: The Pile

Neuron 915 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: 0.1323. Min Range: -0.1323

Max Act: 0.1323. Min Act: -0.0000

Data Index: 539774 (The Pile)

Max Activating Token Index: 146

Text #1

Max Range: 0.1323. Min Range: -0.1323

Max Act: 0.0347. Min Act: -0.0000

Data Index: 1502667 (The Pile)

Max Activating Token Index: 783

Text #2

Max Range: 0.1323. Min Range: -0.1323

Max Act: 0.1189. Min Act: -0.0000

Data Index: 189893 (The Pile)

Max Activating Token Index: 275

Text #3

Max Range: 0.1323. Min Range: -0.1323

Max Act: 0.1146. Min Act: -0.0000

Data Index: 588207 (The Pile)

Max Activating Token Index: 774

Text #4

Max Range: 0.1323. Min Range: -0.1323

Max Act: 0.1049. Min Act: -0.0000

Data Index: 1718283 (The Pile)

Max Activating Token Index: 1019

Text #5

Max Range: 0.1323. Min Range: -0.1323

Max Act: 0.1167. Min Act: -0.0000

Data Index: 514430 (The Pile)

Max Activating Token Index: 443

Text #6

Max Range: 0.1323. Min Range: -0.1323

Max Act: 0.1060. Min Act: -0.0000

Data Index: 1055006 (The Pile)

Max Activating Token Index: 369

Text #7

Max Range: 0.1323. Min Range: -0.1323

Max Act: 0.1010. Min Act: -0.0000

Data Index: 1132681 (The Pile)

Max Activating Token Index: 178

Text #8

Max Range: 0.1323. Min Range: -0.1323

Max Act: 0.0992. Min Act: -0.0000

Data Index: 309319 (The Pile)

Max Activating Token Index: 736

Text #9

Max Range: 0.1323. Min Range: -0.1323

Max Act: 0.0933. Min Act: -0.0000

Data Index: 1558153 (The Pile)

Max Activating Token Index: 199

Text #10

Max Range: 0.1323. Min Range: -0.1323

Max Act: 0.0934. Min Act: -0.0000

Data Index: 917183 (The Pile)

Max Activating Token Index: 80

Text #11

Max Range: 0.1323. Min Range: -0.1323

Max Act: 0.0952. Min Act: -0.0000

Data Index: 427470 (The Pile)

Max Activating Token Index: 58

Text #12

Max Range: 0.1323. Min Range: -0.1323

Max Act: 0.0970. Min Act: -0.0000

Data Index: 259691 (The Pile)

Max Activating Token Index: 828

Text #13

Max Range: 0.1323. Min Range: -0.1323

Max Act: 0.0979. Min Act: -0.0000

Data Index: 754644 (The Pile)

Max Activating Token Index: 835

Text #14

Max Range: 0.1323. Min Range: -0.1323

Max Act: 0.0943. Min Act: -0.0000

Data Index: 639161 (The Pile)

Max Activating Token Index: 1008

Text #15

Max Range: 0.1323. Min Range: -0.1323

Max Act: 0.0887. Min Act: -0.0000

Data Index: 457065 (The Pile)

Max Activating Token Index: 376

Text #16

Max Range: 0.1323. Min Range: -0.1323

Max Act: 0.0929. Min Act: -0.0000

Data Index: 209042 (The Pile)

Max Activating Token Index: 89

Text #17

Max Range: 0.1323. Min Range: -0.1323

Max Act: 0.0841. Min Act: -0.0000

Data Index: 811821 (The Pile)

Max Activating Token Index: 388

Text #18

Max Range: 0.1323. Min Range: -0.1323

Max Act: 0.0884. Min Act: -0.0000

Data Index: 458911 (The Pile)

Max Activating Token Index: 485

Text #19

Max Range: 0.1323. Min Range: -0.1323

Max Act: 0.0820. Min Act: -0.0000

Data Index: 1555614 (The Pile)

Max Activating Token Index: 921