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

Dataset: The Pile

Neuron 4641 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: 0.6248. Min Range: -0.6248

Max Act: 0.6248. Min Act: -0.0000

Data Index: 297068 (The Pile)

Max Activating Token Index: 406

Text #1

Max Range: 0.6248. Min Range: -0.6248

Max Act: 0.5370. Min Act: -0.0000

Data Index: 977832 (The Pile)

Max Activating Token Index: 63

Text #2

Max Range: 0.6248. Min Range: -0.6248

Max Act: 0.5449. Min Act: -0.0000

Data Index: 896170 (The Pile)

Max Activating Token Index: 162

Text #3

Max Range: 0.6248. Min Range: -0.6248

Max Act: 0.5069. Min Act: -0.0000

Data Index: 804493 (The Pile)

Max Activating Token Index: 1005

Text #4

Max Range: 0.6248. Min Range: -0.6248

Max Act: 0.5024. Min Act: -0.0000

Data Index: 1283803 (The Pile)

Max Activating Token Index: 88

Text #5

Max Range: 0.6248. Min Range: -0.6248

Max Act: 0.4973. Min Act: -0.0000

Data Index: 843241 (The Pile)

Max Activating Token Index: 780

Text #6

Max Range: 0.6248. Min Range: -0.6248

Max Act: 0.4452. Min Act: -0.0000

Data Index: 1584038 (The Pile)

Max Activating Token Index: 49

Text #7

Max Range: 0.6248. Min Range: -0.6248

Max Act: 0.4512. Min Act: -0.0000

Data Index: 1964214 (The Pile)

Max Activating Token Index: 97

Text #8

Max Range: 0.6248. Min Range: -0.6248

Max Act: 0.4663. Min Act: -0.0000

Data Index: 101620 (The Pile)

Max Activating Token Index: 621

Text #9

Max Range: 0.6248. Min Range: -0.6248

Max Act: 0.5022. Min Act: -0.0000

Data Index: 763951 (The Pile)

Max Activating Token Index: 150

Text #10

Max Range: 0.6248. Min Range: -0.6248

Max Act: 0.4923. Min Act: -0.0000

Data Index: 573100 (The Pile)

Max Activating Token Index: 345

Text #11

Max Range: 0.6248. Min Range: -0.6248

Max Act: 0.4580. Min Act: -0.0000

Data Index: 832533 (The Pile)

Max Activating Token Index: 239

Text #12

Max Range: 0.6248. Min Range: -0.6248

Max Act: 0.4393. Min Act: -0.0000

Data Index: 1724608 (The Pile)

Max Activating Token Index: 172

Text #13

Max Range: 0.6248. Min Range: -0.6248

Max Act: 0.4238. Min Act: -0.0000

Data Index: 127104 (The Pile)

Max Activating Token Index: 851

Text #14

Max Range: 0.6248. Min Range: -0.6248

Max Act: 0.4475. Min Act: -0.0000

Data Index: 175424 (The Pile)

Max Activating Token Index: 870

Text #15

Max Range: 0.6248. Min Range: -0.6248

Max Act: 0.4324. Min Act: -0.0000

Data Index: 1771041 (The Pile)

Max Activating Token Index: 395

Text #16

Max Range: 0.6248. Min Range: -0.6248

Max Act: 0.4317. Min Act: -0.0000

Data Index: 1784177 (The Pile)

Max Activating Token Index: 193

Text #17

Max Range: 0.6248. Min Range: -0.6248

Max Act: 0.3886. Min Act: -0.0000

Data Index: 1173111 (The Pile)

Max Activating Token Index: 147

Text #18

Max Range: 0.6248. Min Range: -0.6248

Max Act: 0.4066. Min Act: -0.0000

Data Index: 835789 (The Pile)

Max Activating Token Index: 188

Text #19

Max Range: 0.6248. Min Range: -0.6248

Max Act: 0.4033. Min Act: -0.0000

Data Index: 1799642 (The Pile)

Max Activating Token Index: 418