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

Dataset: The Pile

Neuron 564 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.7202. Min Range: -0.7202

Max Act: 0.7202. Min Act: -0.0000

Data Index: 1164492 (The Pile)

Max Activating Token Index: 510

Text #1

Max Range: 0.7202. Min Range: -0.7202

Max Act: 0.5819. Min Act: -0.0000

Data Index: 1872340 (The Pile)

Max Activating Token Index: 264

Text #2

Max Range: 0.7202. Min Range: -0.7202

Max Act: 0.6128. Min Act: -0.0000

Data Index: 1192610 (The Pile)

Max Activating Token Index: 254

Text #3

Max Range: 0.7202. Min Range: -0.7202

Max Act: 0.5542. Min Act: -0.0000

Data Index: 377565 (The Pile)

Max Activating Token Index: 615

Text #4

Max Range: 0.7202. Min Range: -0.7202

Max Act: 0.5359. Min Act: -0.0000

Data Index: 1004558 (The Pile)

Max Activating Token Index: 911

Text #5

Max Range: 0.7202. Min Range: -0.7202

Max Act: 0.5220. Min Act: -0.0000

Data Index: 1664042 (The Pile)

Max Activating Token Index: 583

Text #6

Max Range: 0.7202. Min Range: -0.7202

Max Act: 0.5696. Min Act: -0.0000

Data Index: 73484 (The Pile)

Max Activating Token Index: 491

Text #7

Max Range: 0.7202. Min Range: -0.7202

Max Act: 0.5557. Min Act: -0.0000

Data Index: 1967090 (The Pile)

Max Activating Token Index: 638

Text #8

Max Range: 0.7202. Min Range: -0.7202

Max Act: 0.5387. Min Act: -0.0000

Data Index: 194498 (The Pile)

Max Activating Token Index: 455

Text #9

Max Range: 0.7202. Min Range: -0.7202

Max Act: 0.5195. Min Act: -0.0000

Data Index: 1024176 (The Pile)

Max Activating Token Index: 680

Text #10

Max Range: 0.7202. Min Range: -0.7202

Max Act: 0.5146. Min Act: -0.0000

Data Index: 239525 (The Pile)

Max Activating Token Index: 94

Text #11

Max Range: 0.7202. Min Range: -0.7202

Max Act: 0.5147. Min Act: -0.0000

Data Index: 719274 (The Pile)

Max Activating Token Index: 432

Text #12

Max Range: 0.7202. Min Range: -0.7202

Max Act: 0.5095. Min Act: -0.0000

Data Index: 321549 (The Pile)

Max Activating Token Index: 581

Text #13

Max Range: 0.7202. Min Range: -0.7202

Max Act: 0.4867. Min Act: -0.0000

Data Index: 1498294 (The Pile)

Max Activating Token Index: 417

Text #14

Max Range: 0.7202. Min Range: -0.7202

Max Act: 0.5525. Min Act: -0.0000

Data Index: 1397472 (The Pile)

Max Activating Token Index: 313

Text #15

Max Range: 0.7202. Min Range: -0.7202

Max Act: 0.4991. Min Act: -0.0000

Data Index: 1344215 (The Pile)

Max Activating Token Index: 734

Text #16

Max Range: 0.7202. Min Range: -0.7202

Max Act: 0.5091. Min Act: -0.0000

Data Index: 348146 (The Pile)

Max Activating Token Index: 418

Text #17

Max Range: 0.7202. Min Range: -0.7202

Max Act: 0.4889. Min Act: -0.0000

Data Index: 401974 (The Pile)

Max Activating Token Index: 147

Text #18

Max Range: 0.7202. Min Range: -0.7202

Max Act: 0.4678. Min Act: -0.0000

Data Index: 1146123 (The Pile)

Max Activating Token Index: 264

Text #19

Max Range: 0.7202. Min Range: -0.7202

Max Act: 0.4810. Min Act: -0.0000

Data Index: 1205594 (The Pile)

Max Activating Token Index: 866