Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 4825 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 3.8221. Min Range: -3.8221

Max Act: 3.2797. Min Act: -0.0000

Data Index: 1921150 (The Pile)

Max Activating Token Index: 1018

Text #1

Max Range: 3.8221. Min Range: -3.8221

Max Act: 3.7398. Min Act: -0.0000

Data Index: 396611 (The Pile)

Max Activating Token Index: 544

Text #2

Max Range: 3.8221. Min Range: -3.8221

Max Act: 3.1019. Min Act: -0.0000

Data Index: 1841612 (The Pile)

Max Activating Token Index: 492

Text #3

Max Range: 3.8221. Min Range: -3.8221

Max Act: 3.7023. Min Act: -0.0000

Data Index: 40448 (The Pile)

Max Activating Token Index: 586

Text #4

Max Range: 3.8221. Min Range: -3.8221

Max Act: 3.8221. Min Act: -0.0000

Data Index: 1433846 (The Pile)

Max Activating Token Index: 877

Text #5

Max Range: 3.8221. Min Range: -3.8221

Max Act: 2.7038. Min Act: -0.0000

Data Index: 1300074 (The Pile)

Max Activating Token Index: 796

Text #6

Max Range: 3.8221. Min Range: -3.8221

Max Act: 3.3588. Min Act: -0.0000

Data Index: 787687 (The Pile)

Max Activating Token Index: 549

Text #7

Max Range: 3.8221. Min Range: -3.8221

Max Act: 3.3382. Min Act: -0.0000

Data Index: 212005 (The Pile)

Max Activating Token Index: 515

Text #8

Max Range: 3.8221. Min Range: -3.8221

Max Act: 3.3730. Min Act: -0.0000

Data Index: 1632084 (The Pile)

Max Activating Token Index: 882

Text #9

Max Range: 3.8221. Min Range: -3.8221

Max Act: 3.0217. Min Act: -0.0000

Data Index: 172526 (The Pile)

Max Activating Token Index: 58

Text #10

Max Range: 3.8221. Min Range: -3.8221

Max Act: 3.0760. Min Act: -0.0000

Data Index: 496302 (The Pile)

Max Activating Token Index: 132

Text #11

Max Range: 3.8221. Min Range: -3.8221

Max Act: 2.5028. Min Act: -0.0000

Data Index: 1217397 (The Pile)

Max Activating Token Index: 639

Text #12

Max Range: 3.8221. Min Range: -3.8221

Max Act: 3.0993. Min Act: -0.0000

Data Index: 683601 (The Pile)

Max Activating Token Index: 113

Text #13

Max Range: 3.8221. Min Range: -3.8221

Max Act: 3.2444. Min Act: -0.0000

Data Index: 184533 (The Pile)

Max Activating Token Index: 979

Text #14

Max Range: 3.8221. Min Range: -3.8221

Max Act: 2.9215. Min Act: -0.0000

Data Index: 1520854 (The Pile)

Max Activating Token Index: 471

Text #15

Max Range: 3.8221. Min Range: -3.8221

Max Act: 2.7755. Min Act: -0.0000

Data Index: 1819193 (The Pile)

Max Activating Token Index: 379

Text #16

Max Range: 3.8221. Min Range: -3.8221

Max Act: 2.7693. Min Act: -0.0000

Data Index: 1666330 (The Pile)

Max Activating Token Index: 388

Text #17

Max Range: 3.8221. Min Range: -3.8221

Max Act: 2.9749. Min Act: -0.0000

Data Index: 2787 (The Pile)

Max Activating Token Index: 497

Text #18

Max Range: 3.8221. Min Range: -3.8221

Max Act: 2.8431. Min Act: -0.0000

Data Index: 976373 (The Pile)

Max Activating Token Index: 307

Text #19

Max Range: 3.8221. Min Range: -3.8221

Max Act: 2.8136. Min Act: -0.0000

Data Index: 1351540 (The Pile)

Max Activating Token Index: 600