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

Dataset: The Pile

Neuron 4383 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6223. Min Range: -1.6223

Max Act: 1.5991. Min Act: -0.0000

Data Index: 752583 (The Pile)

Max Activating Token Index: 72

Text #1

Max Range: 1.6223. Min Range: -1.6223

Max Act: 1.5599. Min Act: -0.0000

Data Index: 677585 (The Pile)

Max Activating Token Index: 157

Text #2

Max Range: 1.6223. Min Range: -1.6223

Max Act: 1.3448. Min Act: -0.0000

Data Index: 1061791 (The Pile)

Max Activating Token Index: 61

Text #3

Max Range: 1.6223. Min Range: -1.6223

Max Act: 1.5265. Min Act: -0.0000

Data Index: 1892132 (The Pile)

Max Activating Token Index: 241

Text #4

Max Range: 1.6223. Min Range: -1.6223

Max Act: 1.6223. Min Act: -0.0000

Data Index: 1394281 (The Pile)

Max Activating Token Index: 65

Text #5

Max Range: 1.6223. Min Range: -1.6223

Max Act: 1.2864. Min Act: -0.0000

Data Index: 179308 (The Pile)

Max Activating Token Index: 213

Text #6

Max Range: 1.6223. Min Range: -1.6223

Max Act: 1.3748. Min Act: -0.0000

Data Index: 167273 (The Pile)

Max Activating Token Index: 460

Text #7

Max Range: 1.6223. Min Range: -1.6223

Max Act: 1.4794. Min Act: -0.0000

Data Index: 1114562 (The Pile)

Max Activating Token Index: 1018

Text #8

Max Range: 1.6223. Min Range: -1.6223

Max Act: 1.3893. Min Act: -0.0000

Data Index: 57270 (The Pile)

Max Activating Token Index: 317

Text #9

Max Range: 1.6223. Min Range: -1.6223

Max Act: 1.0985. Min Act: -0.0000

Data Index: 1456466 (The Pile)

Max Activating Token Index: 475

Text #10

Max Range: 1.6223. Min Range: -1.6223

Max Act: 1.0638. Min Act: -0.0000

Data Index: 827050 (The Pile)

Max Activating Token Index: 590

Text #11

Max Range: 1.6223. Min Range: -1.6223

Max Act: 1.0670. Min Act: -0.0000

Data Index: 736103 (The Pile)

Max Activating Token Index: 683

Text #12

Max Range: 1.6223. Min Range: -1.6223

Max Act: 0.9891. Min Act: -0.0000

Data Index: 1849864 (The Pile)

Max Activating Token Index: 585

Text #13

Max Range: 1.6223. Min Range: -1.6223

Max Act: 0.9818. Min Act: -0.0000

Data Index: 1937099 (The Pile)

Max Activating Token Index: 751

Text #14

Max Range: 1.6223. Min Range: -1.6223

Max Act: 1.0880. Min Act: -0.0000

Data Index: 1120136 (The Pile)

Max Activating Token Index: 732

Text #15

Max Range: 1.6223. Min Range: -1.6223

Max Act: 0.9406. Min Act: -0.0000

Data Index: 1793773 (The Pile)

Max Activating Token Index: 988

Text #16

Max Range: 1.6223. Min Range: -1.6223

Max Act: 0.9424. Min Act: -0.0000

Data Index: 1232138 (The Pile)

Max Activating Token Index: 696

Text #17

Max Range: 1.6223. Min Range: -1.6223

Max Act: 1.0540. Min Act: -0.0000

Data Index: 1930920 (The Pile)

Max Activating Token Index: 1001

Text #18

Max Range: 1.6223. Min Range: -1.6223

Max Act: 1.0664. Min Act: -0.0000

Data Index: 1051030 (The Pile)

Max Activating Token Index: 598

Text #19

Max Range: 1.6223. Min Range: -1.6223

Max Act: 0.8623. Min Act: -0.0000

Data Index: 221227 (The Pile)

Max Activating Token Index: 459