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

Dataset: The Pile

Neuron 3053 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: 1.6241. Min Range: -1.6241

Max Act: 1.6241. Min Act: -0.0000

Data Index: 876062 (The Pile)

Max Activating Token Index: 483

Text #1

Max Range: 1.6241. Min Range: -1.6241

Max Act: 1.4625. Min Act: -0.0000

Data Index: 1601520 (The Pile)

Max Activating Token Index: 697

Text #2

Max Range: 1.6241. Min Range: -1.6241

Max Act: 1.5326. Min Act: -0.0000

Data Index: 586558 (The Pile)

Max Activating Token Index: 405

Text #3

Max Range: 1.6241. Min Range: -1.6241

Max Act: 1.4488. Min Act: -0.0000

Data Index: 1581860 (The Pile)

Max Activating Token Index: 395

Text #4

Max Range: 1.6241. Min Range: -1.6241

Max Act: 1.5368. Min Act: -0.0000

Data Index: 1682952 (The Pile)

Max Activating Token Index: 543

Text #5

Max Range: 1.6241. Min Range: -1.6241

Max Act: 1.4328. Min Act: -0.0000

Data Index: 143032 (The Pile)

Max Activating Token Index: 600

Text #6

Max Range: 1.6241. Min Range: -1.6241

Max Act: 1.5140. Min Act: -0.0000

Data Index: 275482 (The Pile)

Max Activating Token Index: 186

Text #7

Max Range: 1.6241. Min Range: -1.6241

Max Act: 1.4966. Min Act: -0.0000

Data Index: 572838 (The Pile)

Max Activating Token Index: 364

Text #8

Max Range: 1.6241. Min Range: -1.6241

Max Act: 1.4551. Min Act: -0.0000

Data Index: 1232291 (The Pile)

Max Activating Token Index: 446

Text #9

Max Range: 1.6241. Min Range: -1.6241

Max Act: 1.4412. Min Act: -0.0000

Data Index: 601020 (The Pile)

Max Activating Token Index: 444

Text #10

Max Range: 1.6241. Min Range: -1.6241

Max Act: 1.4025. Min Act: -0.0000

Data Index: 617721 (The Pile)

Max Activating Token Index: 364

Text #11

Max Range: 1.6241. Min Range: -1.6241

Max Act: 1.4298. Min Act: -0.0000

Data Index: 1342077 (The Pile)

Max Activating Token Index: 528

Text #12

Max Range: 1.6241. Min Range: -1.6241

Max Act: 1.4791. Min Act: -0.0000

Data Index: 801045 (The Pile)

Max Activating Token Index: 497

Text #13

Max Range: 1.6241. Min Range: -1.6241

Max Act: 1.4653. Min Act: -0.0000

Data Index: 809390 (The Pile)

Max Activating Token Index: 188

Text #14

Max Range: 1.6241. Min Range: -1.6241

Max Act: 1.4622. Min Act: -0.0000

Data Index: 1766402 (The Pile)

Max Activating Token Index: 651

Text #15

Max Range: 1.6241. Min Range: -1.6241

Max Act: 1.4576. Min Act: -0.0000

Data Index: 880730 (The Pile)

Max Activating Token Index: 825

Text #16

Max Range: 1.6241. Min Range: -1.6241

Max Act: 1.5012. Min Act: -0.0000

Data Index: 1969678 (The Pile)

Max Activating Token Index: 312

Text #17

Max Range: 1.6241. Min Range: -1.6241

Max Act: 1.4142. Min Act: -0.0000

Data Index: 997658 (The Pile)

Max Activating Token Index: 348

Text #18

Max Range: 1.6241. Min Range: -1.6241

Max Act: 1.4859. Min Act: -0.0000

Data Index: 360195 (The Pile)

Max Activating Token Index: 483

Text #19

Max Range: 1.6241. Min Range: -1.6241

Max Act: 1.3644. Min Act: -0.0000

Data Index: 277555 (The Pile)

Max Activating Token Index: 192