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

Dataset: The Pile

Neuron 3246 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: 0.6436. Min Range: -0.6436

Max Act: 0.5988. Min Act: -0.0000

Data Index: 1175860 (The Pile)

Max Activating Token Index: 796

Text #1

Max Range: 0.6436. Min Range: -0.6436

Max Act: 0.6290. Min Act: -0.0000

Data Index: 1396185 (The Pile)

Max Activating Token Index: 792

Text #2

Max Range: 0.6436. Min Range: -0.6436

Max Act: 0.5790. Min Act: -0.0000

Data Index: 414520 (The Pile)

Max Activating Token Index: 629

Text #3

Max Range: 0.6436. Min Range: -0.6436

Max Act: 0.5463. Min Act: -0.0000

Data Index: 915966 (The Pile)

Max Activating Token Index: 388

Text #4

Max Range: 0.6436. Min Range: -0.6436

Max Act: 0.5764. Min Act: -0.0000

Data Index: 1284577 (The Pile)

Max Activating Token Index: 271

Text #5

Max Range: 0.6436. Min Range: -0.6436

Max Act: 0.6436. Min Act: -0.0000

Data Index: 1300204 (The Pile)

Max Activating Token Index: 756

Text #6

Max Range: 0.6436. Min Range: -0.6436

Max Act: 0.5848. Min Act: -0.0000

Data Index: 1557301 (The Pile)

Max Activating Token Index: 549

Text #7

Max Range: 0.6436. Min Range: -0.6436

Max Act: 0.5281. Min Act: -0.0000

Data Index: 944765 (The Pile)

Max Activating Token Index: 560

Text #8

Max Range: 0.6436. Min Range: -0.6436

Max Act: 0.5956. Min Act: -0.0000

Data Index: 1483159 (The Pile)

Max Activating Token Index: 637

Text #9

Max Range: 0.6436. Min Range: -0.6436

Max Act: 0.5287. Min Act: -0.0000

Data Index: 1270227 (The Pile)

Max Activating Token Index: 378

Text #10

Max Range: 0.6436. Min Range: -0.6436

Max Act: 0.5317. Min Act: -0.0000

Data Index: 1711214 (The Pile)

Max Activating Token Index: 486

Text #11

Max Range: 0.6436. Min Range: -0.6436

Max Act: 0.4855. Min Act: -0.0000

Data Index: 933289 (The Pile)

Max Activating Token Index: 24

Text #12

Max Range: 0.6436. Min Range: -0.6436

Max Act: 0.4961. Min Act: -0.0000

Data Index: 671461 (The Pile)

Max Activating Token Index: 195

Text #13

Max Range: 0.6436. Min Range: -0.6436

Max Act: 0.5245. Min Act: -0.0000

Data Index: 117207 (The Pile)

Max Activating Token Index: 798

Text #14

Max Range: 0.6436. Min Range: -0.6436

Max Act: 0.4731. Min Act: -0.0000

Data Index: 875211 (The Pile)

Max Activating Token Index: 974

Text #15

Max Range: 0.6436. Min Range: -0.6436

Max Act: 0.4758. Min Act: -0.0000

Data Index: 1685581 (The Pile)

Max Activating Token Index: 929

Text #16

Max Range: 0.6436. Min Range: -0.6436

Max Act: 0.5175. Min Act: -0.0000

Data Index: 768395 (The Pile)

Max Activating Token Index: 512

Text #17

Max Range: 0.6436. Min Range: -0.6436

Max Act: 0.4770. Min Act: -0.0000

Data Index: 1619811 (The Pile)

Max Activating Token Index: 163

Text #18

Max Range: 0.6436. Min Range: -0.6436

Max Act: 0.4570. Min Act: -0.0000

Data Index: 1271576 (The Pile)

Max Activating Token Index: 379

Text #19

Max Range: 0.6436. Min Range: -0.6436

Max Act: 0.4487. Min Act: -0.0000

Data Index: 725848 (The Pile)

Max Activating Token Index: 85