Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 52 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')

Text #0

Max Range: 0.6448. Min Range: -0.6448

Max Act: 0.6031. Min Act: -0.0000

Data Index: 875769 (The Pile)

Max Activating Token Index: 45

Text #1

Max Range: 0.6448. Min Range: -0.6448

Max Act: 0.6448. Min Act: 0.0000

Data Index: 1691468 (The Pile)

Max Activating Token Index: 115

Text #2

Max Range: 0.6448. Min Range: -0.6448

Max Act: 0.5883. Min Act: -0.0000

Data Index: 967500 (The Pile)

Max Activating Token Index: 222

Text #3

Max Range: 0.6448. Min Range: -0.6448

Max Act: 0.6013. Min Act: 0.0000

Data Index: 970688 (The Pile)

Max Activating Token Index: 102

Text #4

Max Range: 0.6448. Min Range: -0.6448

Max Act: 0.5737. Min Act: -0.0001

Data Index: 1384946 (The Pile)

Max Activating Token Index: 357

Text #5

Max Range: 0.6448. Min Range: -0.6448

Max Act: 0.5670. Min Act: -0.0001

Data Index: 641895 (The Pile)

Max Activating Token Index: 995

Text #6

Max Range: 0.6448. Min Range: -0.6448

Max Act: 0.5484. Min Act: -0.0000

Data Index: 421915 (The Pile)

Max Activating Token Index: 157

Text #7

Max Range: 0.6448. Min Range: -0.6448

Max Act: 0.5598. Min Act: -0.0000

Data Index: 104508 (The Pile)

Max Activating Token Index: 409

Text #8

Max Range: 0.6448. Min Range: -0.6448

Max Act: 0.5462. Min Act: -0.0000

Data Index: 1188909 (The Pile)

Max Activating Token Index: 530

Text #9

Max Range: 0.6448. Min Range: -0.6448

Max Act: 0.5377. Min Act: -0.0000

Data Index: 1735459 (The Pile)

Max Activating Token Index: 230

Text #10

Max Range: 0.6448. Min Range: -0.6448

Max Act: 0.5586. Min Act: -0.0001

Data Index: 1692765 (The Pile)

Max Activating Token Index: 737

Text #11

Max Range: 0.6448. Min Range: -0.6448

Max Act: 0.5586. Min Act: -0.0000

Data Index: 246251 (The Pile)

Max Activating Token Index: 365

Text #12

Max Range: 0.6448. Min Range: -0.6448

Max Act: 0.5597. Min Act: -0.0000

Data Index: 1151651 (The Pile)

Max Activating Token Index: 648

Text #13

Max Range: 0.6448. Min Range: -0.6448

Max Act: 0.5366. Min Act: -0.0000

Data Index: 1743584 (The Pile)

Max Activating Token Index: 390

Text #14

Max Range: 0.6448. Min Range: -0.6448

Max Act: 0.5298. Min Act: -0.0000

Data Index: 279396 (The Pile)

Max Activating Token Index: 690

Text #15

Max Range: 0.6448. Min Range: -0.6448

Max Act: 0.5281. Min Act: -0.0000

Data Index: 1329630 (The Pile)

Max Activating Token Index: 175

Text #16

Max Range: 0.6448. Min Range: -0.6448

Max Act: 0.5466. Min Act: -0.0000

Data Index: 1329808 (The Pile)

Max Activating Token Index: 491

Text #17

Max Range: 0.6448. Min Range: -0.6448

Max Act: 0.5274. Min Act: -0.0000

Data Index: 662763 (The Pile)

Max Activating Token Index: 505

Text #18

Max Range: 0.6448. Min Range: -0.6448

Max Act: 0.4966. Min Act: -0.0000

Data Index: 137432 (The Pile)

Max Activating Token Index: 369

Text #19

Max Range: 0.6448. Min Range: -0.6448

Max Act: 0.5066. Min Act: -0.0000

Data Index: 358705 (The Pile)

Max Activating Token Index: 275