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

Dataset: The Pile

Neuron 1075 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5980. Min Range: -1.5980

Max Act: 1.5980. Min Act: -0.0000

Data Index: 523818 (The Pile)

Max Activating Token Index: 599

Text #1

Max Range: 1.5980. Min Range: -1.5980

Max Act: 1.4524. Min Act: -0.0000

Data Index: 286548 (The Pile)

Max Activating Token Index: 606

Text #2

Max Range: 1.5980. Min Range: -1.5980

Max Act: 1.1720. Min Act: -0.0000

Data Index: 701932 (The Pile)

Max Activating Token Index: 683

Text #3

Max Range: 1.5980. Min Range: -1.5980

Max Act: 1.2300. Min Act: -0.0000

Data Index: 895879 (The Pile)

Max Activating Token Index: 161

Text #4

Max Range: 1.5980. Min Range: -1.5980

Max Act: 1.1393. Min Act: -0.0000

Data Index: 583203 (The Pile)

Max Activating Token Index: 534

Text #5

Max Range: 1.5980. Min Range: -1.5980

Max Act: 1.1474. Min Act: -0.0000

Data Index: 231356 (The Pile)

Max Activating Token Index: 689

Text #6

Max Range: 1.5980. Min Range: -1.5980

Max Act: 1.1992. Min Act: -0.0000

Data Index: 1352815 (The Pile)

Max Activating Token Index: 172

Text #7

Max Range: 1.5980. Min Range: -1.5980

Max Act: 1.0136. Min Act: -0.0000

Data Index: 367271 (The Pile)

Max Activating Token Index: 579

Text #8

Max Range: 1.5980. Min Range: -1.5980

Max Act: 1.0315. Min Act: -0.0000

Data Index: 871139 (The Pile)

Max Activating Token Index: 347

Text #9

Max Range: 1.5980. Min Range: -1.5980

Max Act: 0.8940. Min Act: -0.0000

Data Index: 360523 (The Pile)

Max Activating Token Index: 568

Text #10

Max Range: 1.5980. Min Range: -1.5980

Max Act: 0.9675. Min Act: -0.0000

Data Index: 1516854 (The Pile)

Max Activating Token Index: 119

Text #11

Max Range: 1.5980. Min Range: -1.5980

Max Act: 0.9424. Min Act: -0.0000

Data Index: 1394909 (The Pile)

Max Activating Token Index: 563

Text #12

Max Range: 1.5980. Min Range: -1.5980

Max Act: 0.9842. Min Act: -0.0000

Data Index: 1329728 (The Pile)

Max Activating Token Index: 260

Text #13

Max Range: 1.5980. Min Range: -1.5980

Max Act: 0.7966. Min Act: -0.0000

Data Index: 816091 (The Pile)

Max Activating Token Index: 577

Text #14

Max Range: 1.5980. Min Range: -1.5980

Max Act: 0.9055. Min Act: -0.0000

Data Index: 693723 (The Pile)

Max Activating Token Index: 966

Text #15

Max Range: 1.5980. Min Range: -1.5980

Max Act: 0.7986. Min Act: -0.0000

Data Index: 1528022 (The Pile)

Max Activating Token Index: 746

Text #16

Max Range: 1.5980. Min Range: -1.5980

Max Act: 0.7714. Min Act: -0.0000

Data Index: 1156986 (The Pile)

Max Activating Token Index: 130

Text #17

Max Range: 1.5980. Min Range: -1.5980

Max Act: 0.8329. Min Act: -0.0000

Data Index: 1727657 (The Pile)

Max Activating Token Index: 734

Text #18

Max Range: 1.5980. Min Range: -1.5980

Max Act: 0.7615. Min Act: -0.0000

Data Index: 587909 (The Pile)

Max Activating Token Index: 22

Text #19

Max Range: 1.5980. Min Range: -1.5980

Max Act: 0.7754. Min Act: -0.0000

Data Index: 1230409 (The Pile)

Max Activating Token Index: 109