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

Dataset: The Pile

Neuron 218 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2274. Min Range: -1.2274

Max Act: 1.2274. Min Act: -0.0000

Data Index: 632696 (The Pile)

Max Activating Token Index: 777

Text #1

Max Range: 1.2274. Min Range: -1.2274

Max Act: 1.1207. Min Act: -0.0000

Data Index: 678666 (The Pile)

Max Activating Token Index: 114

Text #2

Max Range: 1.2274. Min Range: -1.2274

Max Act: 1.0902. Min Act: -0.0000

Data Index: 1404662 (The Pile)

Max Activating Token Index: 120

Text #3

Max Range: 1.2274. Min Range: -1.2274

Max Act: 1.1040. Min Act: -0.0000

Data Index: 722278 (The Pile)

Max Activating Token Index: 783

Text #4

Max Range: 1.2274. Min Range: -1.2274

Max Act: 1.1629. Min Act: -0.0000

Data Index: 1112966 (The Pile)

Max Activating Token Index: 264

Text #5

Max Range: 1.2274. Min Range: -1.2274

Max Act: 1.0929. Min Act: -0.0000

Data Index: 1511868 (The Pile)

Max Activating Token Index: 140

Text #6

Max Range: 1.2274. Min Range: -1.2274

Max Act: 1.1166. Min Act: -0.0000

Data Index: 650051 (The Pile)

Max Activating Token Index: 76

Text #7

Max Range: 1.2274. Min Range: -1.2274

Max Act: 1.0940. Min Act: -0.0000

Data Index: 563577 (The Pile)

Max Activating Token Index: 326

Text #8

Max Range: 1.2274. Min Range: -1.2274

Max Act: 1.0093. Min Act: -0.0000

Data Index: 1470179 (The Pile)

Max Activating Token Index: 387

Text #9

Max Range: 1.2274. Min Range: -1.2274

Max Act: 0.8921. Min Act: -0.0000

Data Index: 642201 (The Pile)

Max Activating Token Index: 191

Text #10

Max Range: 1.2274. Min Range: -1.2274

Max Act: 0.9017. Min Act: -0.0000

Data Index: 1135200 (The Pile)

Max Activating Token Index: 980

Text #11

Max Range: 1.2274. Min Range: -1.2274

Max Act: 1.0681. Min Act: -0.0000

Data Index: 1785313 (The Pile)

Max Activating Token Index: 772

Text #12

Max Range: 1.2274. Min Range: -1.2274

Max Act: 0.9694. Min Act: -0.0000

Data Index: 543235 (The Pile)

Max Activating Token Index: 168

Text #13

Max Range: 1.2274. Min Range: -1.2274

Max Act: 0.9125. Min Act: -0.0000

Data Index: 819029 (The Pile)

Max Activating Token Index: 764

Text #14

Max Range: 1.2274. Min Range: -1.2274

Max Act: 0.9217. Min Act: -0.0000

Data Index: 1346758 (The Pile)

Max Activating Token Index: 225

Text #15

Max Range: 1.2274. Min Range: -1.2274

Max Act: 0.8715. Min Act: -0.0000

Data Index: 995872 (The Pile)

Max Activating Token Index: 190

Text #16

Max Range: 1.2274. Min Range: -1.2274

Max Act: 0.8462. Min Act: -0.0000

Data Index: 1736690 (The Pile)

Max Activating Token Index: 625

Text #17

Max Range: 1.2274. Min Range: -1.2274

Max Act: 0.9662. Min Act: -0.0000

Data Index: 1650748 (The Pile)

Max Activating Token Index: 169

Text #18

Max Range: 1.2274. Min Range: -1.2274

Max Act: 0.8636. Min Act: -0.0000

Data Index: 1108248 (The Pile)

Max Activating Token Index: 596

Text #19

Max Range: 1.2274. Min Range: -1.2274

Max Act: 0.9387. Min Act: -0.0000

Data Index: 539537 (The Pile)

Max Activating Token Index: 171