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

Dataset: The Pile

Neuron 4819 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: 0.1237. Min Range: -0.1237

Max Act: 0.0981. Min Act: -0.0000

Data Index: 1108308 (The Pile)

Max Activating Token Index: 283

Text #1

Max Range: 0.1237. Min Range: -0.1237

Max Act: 0.1237. Min Act: -0.0000

Data Index: 678681 (The Pile)

Max Activating Token Index: 800

Text #2

Max Range: 0.1237. Min Range: -0.1237

Max Act: 0.0962. Min Act: -0.0000

Data Index: 800001 (The Pile)

Max Activating Token Index: 874

Text #3

Max Range: 0.1237. Min Range: -0.1237

Max Act: 0.1174. Min Act: -0.0000

Data Index: 1137575 (The Pile)

Max Activating Token Index: 649

Text #4

Max Range: 0.1237. Min Range: -0.1237

Max Act: 0.1129. Min Act: -0.0000

Data Index: 964080 (The Pile)

Max Activating Token Index: 599

Text #5

Max Range: 0.1237. Min Range: -0.1237

Max Act: 0.1215. Min Act: -0.0000

Data Index: 477238 (The Pile)

Max Activating Token Index: 831

Text #6

Max Range: 0.1237. Min Range: -0.1237

Max Act: 0.1084. Min Act: -0.0000

Data Index: 428620 (The Pile)

Max Activating Token Index: 530

Text #7

Max Range: 0.1237. Min Range: -0.1237

Max Act: 0.1063. Min Act: -0.0000

Data Index: 350330 (The Pile)

Max Activating Token Index: 669

Text #8

Max Range: 0.1237. Min Range: -0.1237

Max Act: 0.1066. Min Act: -0.0000

Data Index: 1107306 (The Pile)

Max Activating Token Index: 488

Text #9

Max Range: 0.1237. Min Range: -0.1237

Max Act: 0.1106. Min Act: -0.0000

Data Index: 1053337 (The Pile)

Max Activating Token Index: 984

Text #10

Max Range: 0.1237. Min Range: -0.1237

Max Act: 0.0990. Min Act: -0.0000

Data Index: 1778322 (The Pile)

Max Activating Token Index: 347

Text #11

Max Range: 0.1237. Min Range: -0.1237

Max Act: 0.0954. Min Act: -0.0000

Data Index: 1258566 (The Pile)

Max Activating Token Index: 797

Text #12

Max Range: 0.1237. Min Range: -0.1237

Max Act: 0.0983. Min Act: -0.0000

Data Index: 1759889 (The Pile)

Max Activating Token Index: 917

Text #13

Max Range: 0.1237. Min Range: -0.1237

Max Act: 0.0980. Min Act: -0.0000

Data Index: 1136912 (The Pile)

Max Activating Token Index: 40

Text #14

Max Range: 0.1237. Min Range: -0.1237

Max Act: 0.1015. Min Act: -0.0000

Data Index: 1825245 (The Pile)

Max Activating Token Index: 235

Text #15

Max Range: 0.1237. Min Range: -0.1237

Max Act: 0.1048. Min Act: -0.0000

Data Index: 852406 (The Pile)

Max Activating Token Index: 376

Text #16

Max Range: 0.1237. Min Range: -0.1237

Max Act: 0.1046. Min Act: -0.0000

Data Index: 811924 (The Pile)

Max Activating Token Index: 24

Text #17

Max Range: 0.1237. Min Range: -0.1237

Max Act: 0.1008. Min Act: -0.0000

Data Index: 633531 (The Pile)

Max Activating Token Index: 194

Text #18

Max Range: 0.1237. Min Range: -0.1237

Max Act: 0.0944. Min Act: -0.0000

Data Index: 732471 (The Pile)

Max Activating Token Index: 666

Text #19

Max Range: 0.1237. Min Range: -0.1237

Max Act: 0.0933. Min Act: -0.0000

Data Index: 144570 (The Pile)

Max Activating Token Index: 509