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

Dataset: The Pile

Neuron 3159 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: 0.9467. Min Range: -0.9467

Max Act: 0.9467. Min Act: -0.0000

Data Index: 1224841 (The Pile)

Max Activating Token Index: 644

Text #1

Max Range: 0.9467. Min Range: -0.9467

Max Act: 0.8244. Min Act: -0.0000

Data Index: 154068 (The Pile)

Max Activating Token Index: 552

Text #2

Max Range: 0.9467. Min Range: -0.9467

Max Act: 0.8760. Min Act: -0.0000

Data Index: 624548 (The Pile)

Max Activating Token Index: 801

Text #3

Max Range: 0.9467. Min Range: -0.9467

Max Act: 0.7473. Min Act: -0.0000

Data Index: 1166951 (The Pile)

Max Activating Token Index: 208

Text #4

Max Range: 0.9467. Min Range: -0.9467

Max Act: 0.7802. Min Act: -0.0000

Data Index: 542027 (The Pile)

Max Activating Token Index: 642

Text #5

Max Range: 0.9467. Min Range: -0.9467

Max Act: 0.7557. Min Act: -0.0000

Data Index: 303299 (The Pile)

Max Activating Token Index: 87

Text #6

Max Range: 0.9467. Min Range: -0.9467

Max Act: 0.7460. Min Act: -0.0000

Data Index: 1002319 (The Pile)

Max Activating Token Index: 388

Text #7

Max Range: 0.9467. Min Range: -0.9467

Max Act: 0.7133. Min Act: 0.0000

Data Index: 114332 (The Pile)

Max Activating Token Index: 445

Text #8

Max Range: 0.9467. Min Range: -0.9467

Max Act: 0.6928. Min Act: -0.0000

Data Index: 1028850 (The Pile)

Max Activating Token Index: 540

Text #9

Max Range: 0.9467. Min Range: -0.9467

Max Act: 0.6855. Min Act: -0.0000

Data Index: 1410274 (The Pile)

Max Activating Token Index: 802

Text #10

Max Range: 0.9467. Min Range: -0.9467

Max Act: 0.6425. Min Act: 0.0000

Data Index: 957288 (The Pile)

Max Activating Token Index: 114

Text #11

Max Range: 0.9467. Min Range: -0.9467

Max Act: 0.6637. Min Act: -0.0000

Data Index: 660776 (The Pile)

Max Activating Token Index: 548

Text #12

Max Range: 0.9467. Min Range: -0.9467

Max Act: 0.6297. Min Act: 0.0000

Data Index: 1159354 (The Pile)

Max Activating Token Index: 219

Text #13

Max Range: 0.9467. Min Range: -0.9467

Max Act: 0.6555. Min Act: -0.0000

Data Index: 46455 (The Pile)

Max Activating Token Index: 183

Text #14

Max Range: 0.9467. Min Range: -0.9467

Max Act: 0.6361. Min Act: 0.0000

Data Index: 707141 (The Pile)

Max Activating Token Index: 868

Text #15

Max Range: 0.9467. Min Range: -0.9467

Max Act: 0.6452. Min Act: -0.0000

Data Index: 913011 (The Pile)

Max Activating Token Index: 895

Text #16

Max Range: 0.9467. Min Range: -0.9467

Max Act: 0.6411. Min Act: -0.0000

Data Index: 1476322 (The Pile)

Max Activating Token Index: 279

Text #17

Max Range: 0.9467. Min Range: -0.9467

Max Act: 0.6168. Min Act: 0.0000

Data Index: 1482889 (The Pile)

Max Activating Token Index: 187

Text #18

Max Range: 0.9467. Min Range: -0.9467

Max Act: 0.6418. Min Act: -0.0000

Data Index: 20316 (The Pile)

Max Activating Token Index: 598

Text #19

Max Range: 0.9467. Min Range: -0.9467

Max Act: 0.6045. Min Act: -0.0000

Data Index: 1600256 (The Pile)

Max Activating Token Index: 636