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

Dataset: The Pile

Neuron 3646 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: 3.0282. Min Range: -3.0282

Max Act: 3.0282. Min Act: -0.0000

Data Index: 327837 (The Pile)

Max Activating Token Index: 152

Text #1

Max Range: 3.0282. Min Range: -3.0282

Max Act: 2.7102. Min Act: -0.0000

Data Index: 1219501 (The Pile)

Max Activating Token Index: 245

Text #2

Max Range: 3.0282. Min Range: -3.0282

Max Act: 2.5404. Min Act: -0.0000

Data Index: 1824749 (The Pile)

Max Activating Token Index: 515

Text #3

Max Range: 3.0282. Min Range: -3.0282

Max Act: 2.4793. Min Act: -0.0000

Data Index: 1529788 (The Pile)

Max Activating Token Index: 291

Text #4

Max Range: 3.0282. Min Range: -3.0282

Max Act: 2.2281. Min Act: -0.0000

Data Index: 1570038 (The Pile)

Max Activating Token Index: 148

Text #5

Max Range: 3.0282. Min Range: -3.0282

Max Act: 2.2958. Min Act: -0.0000

Data Index: 956054 (The Pile)

Max Activating Token Index: 828

Text #6

Max Range: 3.0282. Min Range: -3.0282

Max Act: 2.3077. Min Act: -0.0000

Data Index: 1608679 (The Pile)

Max Activating Token Index: 824

Text #7

Max Range: 3.0282. Min Range: -3.0282

Max Act: 2.3521. Min Act: -0.0000

Data Index: 1345880 (The Pile)

Max Activating Token Index: 447

Text #8

Max Range: 3.0282. Min Range: -3.0282

Max Act: 1.9123. Min Act: -0.0000

Data Index: 524924 (The Pile)

Max Activating Token Index: 856

Text #9

Max Range: 3.0282. Min Range: -3.0282

Max Act: 2.1656. Min Act: -0.0000

Data Index: 1006036 (The Pile)

Max Activating Token Index: 312

Text #10

Max Range: 3.0282. Min Range: -3.0282

Max Act: 2.1626. Min Act: -0.0000

Data Index: 641445 (The Pile)

Max Activating Token Index: 1013

Text #11

Max Range: 3.0282. Min Range: -3.0282

Max Act: 2.0216. Min Act: -0.0000

Data Index: 706069 (The Pile)

Max Activating Token Index: 960

Text #12

Max Range: 3.0282. Min Range: -3.0282

Max Act: 2.2189. Min Act: -0.0000

Data Index: 1120802 (The Pile)

Max Activating Token Index: 568

Text #13

Max Range: 3.0282. Min Range: -3.0282

Max Act: 2.0910. Min Act: -0.0000

Data Index: 295846 (The Pile)

Max Activating Token Index: 696

Text #14

Max Range: 3.0282. Min Range: -3.0282

Max Act: 1.9379. Min Act: -0.0000

Data Index: 941699 (The Pile)

Max Activating Token Index: 112

Text #15

Max Range: 3.0282. Min Range: -3.0282

Max Act: 2.2555. Min Act: -0.0000

Data Index: 631836 (The Pile)

Max Activating Token Index: 753

Text #16

Max Range: 3.0282. Min Range: -3.0282

Max Act: 2.0467. Min Act: -0.0000

Data Index: 1447271 (The Pile)

Max Activating Token Index: 646

Text #17

Max Range: 3.0282. Min Range: -3.0282

Max Act: 2.0987. Min Act: -0.0000

Data Index: 840325 (The Pile)

Max Activating Token Index: 755

Text #18

Max Range: 3.0282. Min Range: -3.0282

Max Act: 2.0069. Min Act: -0.0000

Data Index: 541226 (The Pile)

Max Activating Token Index: 277

Text #19

Max Range: 3.0282. Min Range: -3.0282

Max Act: 2.0077. Min Act: -0.0000

Data Index: 773990 (The Pile)

Max Activating Token Index: 304