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

Dataset: The Pile

Neuron 3098 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: 0.1213. Min Range: -0.1213

Max Act: 0.1213. Min Act: -0.0000

Data Index: 404411 (The Pile)

Max Activating Token Index: 52

Text #1

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.1195. Min Act: -0.0000

Data Index: 246447 (The Pile)

Max Activating Token Index: 393

Text #2

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.1022. Min Act: -0.0000

Data Index: 156954 (The Pile)

Max Activating Token Index: 91

Text #3

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0924. Min Act: -0.0000

Data Index: 1037598 (The Pile)

Max Activating Token Index: 144

Text #4

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0879. Min Act: -0.0000

Data Index: 560755 (The Pile)

Max Activating Token Index: 286

Text #5

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0834. Min Act: -0.0000

Data Index: 835591 (The Pile)

Max Activating Token Index: 900

Text #6

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0965. Min Act: -0.0000

Data Index: 1860158 (The Pile)

Max Activating Token Index: 415

Text #7

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0812. Min Act: -0.0000

Data Index: 549869 (The Pile)

Max Activating Token Index: 375

Text #8

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0856. Min Act: -0.0000

Data Index: 551064 (The Pile)

Max Activating Token Index: 490

Text #9

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0850. Min Act: -0.0000

Data Index: 29243 (The Pile)

Max Activating Token Index: 64

Text #10

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0770. Min Act: -0.0000

Data Index: 850354 (The Pile)

Max Activating Token Index: 187

Text #11

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0847. Min Act: -0.0000

Data Index: 1687117 (The Pile)

Max Activating Token Index: 310

Text #12

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0867. Min Act: -0.0000

Data Index: 524119 (The Pile)

Max Activating Token Index: 757

Text #13

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0897. Min Act: -0.0000

Data Index: 1291729 (The Pile)

Max Activating Token Index: 108

Text #14

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0832. Min Act: -0.0000

Data Index: 998287 (The Pile)

Max Activating Token Index: 63

Text #15

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0796. Min Act: -0.0000

Data Index: 1988191 (The Pile)

Max Activating Token Index: 573

Text #16

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0848. Min Act: -0.0000

Data Index: 892086 (The Pile)

Max Activating Token Index: 341

Text #17

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0824. Min Act: -0.0000

Data Index: 1242404 (The Pile)

Max Activating Token Index: 430

Text #18

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0750. Min Act: -0.0000

Data Index: 473616 (The Pile)

Max Activating Token Index: 326

Text #19

Max Range: 0.1213. Min Range: -0.1213

Max Act: 0.0808. Min Act: -0.0000

Data Index: 447716 (The Pile)

Max Activating Token Index: 347