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

Dataset: The Pile

Neuron 2705 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: 1.6235. Min Range: -1.6235

Max Act: 1.6235. Min Act: -0.0000

Data Index: 1040329 (The Pile)

Max Activating Token Index: 993

Text #1

Max Range: 1.6235. Min Range: -1.6235

Max Act: 1.1813. Min Act: 0.0000

Data Index: 1022487 (The Pile)

Max Activating Token Index: 204

Text #2

Max Range: 1.6235. Min Range: -1.6235

Max Act: 1.1843. Min Act: 0.0000

Data Index: 958288 (The Pile)

Max Activating Token Index: 206

Text #3

Max Range: 1.6235. Min Range: -1.6235

Max Act: 1.1122. Min Act: -0.0000

Data Index: 574912 (The Pile)

Max Activating Token Index: 777

Text #4

Max Range: 1.6235. Min Range: -1.6235

Max Act: 1.1351. Min Act: -0.0000

Data Index: 919113 (The Pile)

Max Activating Token Index: 689

Text #5

Max Range: 1.6235. Min Range: -1.6235

Max Act: 1.1088. Min Act: -0.0000

Data Index: 555631 (The Pile)

Max Activating Token Index: 265

Text #6

Max Range: 1.6235. Min Range: -1.6235

Max Act: 1.1094. Min Act: -0.0000

Data Index: 1699233 (The Pile)

Max Activating Token Index: 218

Text #7

Max Range: 1.6235. Min Range: -1.6235

Max Act: 1.0176. Min Act: -0.0000

Data Index: 289998 (The Pile)

Max Activating Token Index: 88

Text #8

Max Range: 1.6235. Min Range: -1.6235

Max Act: 0.9836. Min Act: -0.0000

Data Index: 776753 (The Pile)

Max Activating Token Index: 389

Text #9

Max Range: 1.6235. Min Range: -1.6235

Max Act: 0.9567. Min Act: -0.0000

Data Index: 1177710 (The Pile)

Max Activating Token Index: 391

Text #10

Max Range: 1.6235. Min Range: -1.6235

Max Act: 0.9044. Min Act: -0.0000

Data Index: 1049368 (The Pile)

Max Activating Token Index: 791

Text #11

Max Range: 1.6235. Min Range: -1.6235

Max Act: 0.8333. Min Act: -0.0000

Data Index: 97771 (The Pile)

Max Activating Token Index: 558

Text #12

Max Range: 1.6235. Min Range: -1.6235

Max Act: 0.9333. Min Act: -0.0000

Data Index: 1804895 (The Pile)

Max Activating Token Index: 968

Text #13

Max Range: 1.6235. Min Range: -1.6235

Max Act: 0.8586. Min Act: -0.0000

Data Index: 940815 (The Pile)

Max Activating Token Index: 784

Text #14

Max Range: 1.6235. Min Range: -1.6235

Max Act: 0.8416. Min Act: -0.0000

Data Index: 266039 (The Pile)

Max Activating Token Index: 658

Text #15

Max Range: 1.6235. Min Range: -1.6235

Max Act: 0.9416. Min Act: -0.0000

Data Index: 1805289 (The Pile)

Max Activating Token Index: 887

Text #16

Max Range: 1.6235. Min Range: -1.6235

Max Act: 0.8219. Min Act: -0.0000

Data Index: 835480 (The Pile)

Max Activating Token Index: 634

Text #17

Max Range: 1.6235. Min Range: -1.6235

Max Act: 0.9363. Min Act: -0.0000

Data Index: 1516439 (The Pile)

Max Activating Token Index: 988

Text #18

Max Range: 1.6235. Min Range: -1.6235

Max Act: 0.6709. Min Act: -0.0000

Data Index: 208764 (The Pile)

Max Activating Token Index: 600

Text #19

Max Range: 1.6235. Min Range: -1.6235

Max Act: 0.6720. Min Act: -0.0000

Data Index: 380826 (The Pile)

Max Activating Token Index: 1009