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

Dataset: The Pile

Neuron 1189 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: 1.6658. Min Range: -1.6658

Max Act: 1.6658. Min Act: -0.0000

Data Index: 194389 (The Pile)

Max Activating Token Index: 25

Text #1

Max Range: 1.6658. Min Range: -1.6658

Max Act: 1.3936. Min Act: -0.0000

Data Index: 1665943 (The Pile)

Max Activating Token Index: 978

Text #2

Max Range: 1.6658. Min Range: -1.6658

Max Act: 1.6253. Min Act: -0.0000

Data Index: 368730 (The Pile)

Max Activating Token Index: 248

Text #3

Max Range: 1.6658. Min Range: -1.6658

Max Act: 1.4849. Min Act: -0.0000

Data Index: 1006057 (The Pile)

Max Activating Token Index: 1023

Text #4

Max Range: 1.6658. Min Range: -1.6658

Max Act: 1.4733. Min Act: -0.0000

Data Index: 677228 (The Pile)

Max Activating Token Index: 453

Text #5

Max Range: 1.6658. Min Range: -1.6658

Max Act: 1.3623. Min Act: -0.0000

Data Index: 927706 (The Pile)

Max Activating Token Index: 819

Text #6

Max Range: 1.6658. Min Range: -1.6658

Max Act: 1.3656. Min Act: -0.0000

Data Index: 76928 (The Pile)

Max Activating Token Index: 295

Text #7

Max Range: 1.6658. Min Range: -1.6658

Max Act: 1.3313. Min Act: -0.0000

Data Index: 492513 (The Pile)

Max Activating Token Index: 386

Text #8

Max Range: 1.6658. Min Range: -1.6658

Max Act: 1.3197. Min Act: -0.0000

Data Index: 1490264 (The Pile)

Max Activating Token Index: 37

Text #9

Max Range: 1.6658. Min Range: -1.6658

Max Act: 1.2831. Min Act: -0.0000

Data Index: 1746583 (The Pile)

Max Activating Token Index: 1016

Text #10

Max Range: 1.6658. Min Range: -1.6658

Max Act: 1.2685. Min Act: -0.0000

Data Index: 689736 (The Pile)

Max Activating Token Index: 955

Text #11

Max Range: 1.6658. Min Range: -1.6658

Max Act: 1.2716. Min Act: -0.0000

Data Index: 596082 (The Pile)

Max Activating Token Index: 231

Text #12

Max Range: 1.6658. Min Range: -1.6658

Max Act: 1.3465. Min Act: -0.0000

Data Index: 1877755 (The Pile)

Max Activating Token Index: 449

Text #13

Max Range: 1.6658. Min Range: -1.6658

Max Act: 1.3383. Min Act: -0.0000

Data Index: 457253 (The Pile)

Max Activating Token Index: 64

Text #14

Max Range: 1.6658. Min Range: -1.6658

Max Act: 1.2662. Min Act: -0.0000

Data Index: 58614 (The Pile)

Max Activating Token Index: 733

Text #15

Max Range: 1.6658. Min Range: -1.6658

Max Act: 1.2755. Min Act: -0.0000

Data Index: 270069 (The Pile)

Max Activating Token Index: 202

Text #16

Max Range: 1.6658. Min Range: -1.6658

Max Act: 1.3326. Min Act: -0.0000

Data Index: 1232405 (The Pile)

Max Activating Token Index: 420

Text #17

Max Range: 1.6658. Min Range: -1.6658

Max Act: 1.3226. Min Act: -0.0000

Data Index: 1379642 (The Pile)

Max Activating Token Index: 958

Text #18

Max Range: 1.6658. Min Range: -1.6658

Max Act: 1.2984. Min Act: -0.0000

Data Index: 1223320 (The Pile)

Max Activating Token Index: 738

Text #19

Max Range: 1.6658. Min Range: -1.6658

Max Act: 1.3806. Min Act: -0.0000

Data Index: 572451 (The Pile)

Max Activating Token Index: 341