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

Dataset: The Pile

Neuron 3421 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: 0.4549. Min Range: -0.4549

Max Act: 0.4309. Min Act: -0.0000

Data Index: 1267538 (The Pile)

Max Activating Token Index: 831

Text #1

Max Range: 0.4549. Min Range: -0.4549

Max Act: 0.4549. Min Act: -0.0000

Data Index: 860918 (The Pile)

Max Activating Token Index: 417

Text #2

Max Range: 0.4549. Min Range: -0.4549

Max Act: 0.4266. Min Act: -0.0000

Data Index: 1297847 (The Pile)

Max Activating Token Index: 888

Text #3

Max Range: 0.4549. Min Range: -0.4549

Max Act: 0.4201. Min Act: -0.0000

Data Index: 1045156 (The Pile)

Max Activating Token Index: 361

Text #4

Max Range: 0.4549. Min Range: -0.4549

Max Act: 0.3884. Min Act: -0.0000

Data Index: 1686342 (The Pile)

Max Activating Token Index: 791

Text #5

Max Range: 0.4549. Min Range: -0.4549

Max Act: 0.4160. Min Act: -0.0000

Data Index: 1047566 (The Pile)

Max Activating Token Index: 346

Text #6

Max Range: 0.4549. Min Range: -0.4549

Max Act: 0.4080. Min Act: -0.0000

Data Index: 1627742 (The Pile)

Max Activating Token Index: 1003

Text #7

Max Range: 0.4549. Min Range: -0.4549

Max Act: 0.4231. Min Act: -0.0000

Data Index: 1545520 (The Pile)

Max Activating Token Index: 808

Text #8

Max Range: 0.4549. Min Range: -0.4549

Max Act: 0.4094. Min Act: -0.0000

Data Index: 615971 (The Pile)

Max Activating Token Index: 799

Text #9

Max Range: 0.4549. Min Range: -0.4549

Max Act: 0.3995. Min Act: -0.0000

Data Index: 1239519 (The Pile)

Max Activating Token Index: 146

Text #10

Max Range: 0.4549. Min Range: -0.4549

Max Act: 0.3944. Min Act: -0.0000

Data Index: 1152745 (The Pile)

Max Activating Token Index: 131

Text #11

Max Range: 0.4549. Min Range: -0.4549

Max Act: 0.4075. Min Act: -0.0000

Data Index: 1048723 (The Pile)

Max Activating Token Index: 43

Text #12

Max Range: 0.4549. Min Range: -0.4549

Max Act: 0.4189. Min Act: -0.0000

Data Index: 1614224 (The Pile)

Max Activating Token Index: 781

Text #13

Max Range: 0.4549. Min Range: -0.4549

Max Act: 0.3903. Min Act: -0.0000

Data Index: 1442076 (The Pile)

Max Activating Token Index: 538

Text #14

Max Range: 0.4549. Min Range: -0.4549

Max Act: 0.3959. Min Act: -0.0000

Data Index: 999521 (The Pile)

Max Activating Token Index: 609

Text #15

Max Range: 0.4549. Min Range: -0.4549

Max Act: 0.3797. Min Act: -0.0000

Data Index: 1386901 (The Pile)

Max Activating Token Index: 24

Text #16

Max Range: 0.4549. Min Range: -0.4549

Max Act: 0.4049. Min Act: -0.0000

Data Index: 1304639 (The Pile)

Max Activating Token Index: 922

Text #17

Max Range: 0.4549. Min Range: -0.4549

Max Act: 0.3902. Min Act: -0.0000

Data Index: 168556 (The Pile)

Max Activating Token Index: 425

Text #18

Max Range: 0.4549. Min Range: -0.4549

Max Act: 0.3785. Min Act: -0.0000

Data Index: 1899270 (The Pile)

Max Activating Token Index: 57

Text #19

Max Range: 0.4549. Min Range: -0.4549

Max Act: 0.3893. Min Act: -0.0000

Data Index: 1012326 (The Pile)

Max Activating Token Index: 104