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

Dataset: The Pile

Neuron 976 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: 0.8292. Min Range: -0.8292

Max Act: 0.8292. Min Act: -0.0000

Data Index: 1358350 (The Pile)

Max Activating Token Index: 900

Text #1

Max Range: 0.8292. Min Range: -0.8292

Max Act: 0.7222. Min Act: -0.0000

Data Index: 22644 (The Pile)

Max Activating Token Index: 508

Text #2

Max Range: 0.8292. Min Range: -0.8292

Max Act: 0.5532. Min Act: -0.0000

Data Index: 1795678 (The Pile)

Max Activating Token Index: 240

Text #3

Max Range: 0.8292. Min Range: -0.8292

Max Act: 0.5958. Min Act: -0.0000

Data Index: 1175794 (The Pile)

Max Activating Token Index: 181

Text #4

Max Range: 0.8292. Min Range: -0.8292

Max Act: 0.5579. Min Act: -0.0000

Data Index: 1800979 (The Pile)

Max Activating Token Index: 853

Text #5

Max Range: 0.8292. Min Range: -0.8292

Max Act: 0.5440. Min Act: 0.0000

Data Index: 39480 (The Pile)

Max Activating Token Index: 213

Text #6

Max Range: 0.8292. Min Range: -0.8292

Max Act: 0.5266. Min Act: -0.0000

Data Index: 131402 (The Pile)

Max Activating Token Index: 791

Text #7

Max Range: 0.8292. Min Range: -0.8292

Max Act: 0.5509. Min Act: -0.0000

Data Index: 386316 (The Pile)

Max Activating Token Index: 448

Text #8

Max Range: 0.8292. Min Range: -0.8292

Max Act: 0.5720. Min Act: 0.0000

Data Index: 1866857 (The Pile)

Max Activating Token Index: 44

Text #9

Max Range: 0.8292. Min Range: -0.8292

Max Act: 0.5503. Min Act: -0.0000

Data Index: 463386 (The Pile)

Max Activating Token Index: 268

Text #10

Max Range: 0.8292. Min Range: -0.8292

Max Act: 0.5495. Min Act: -0.0000

Data Index: 374883 (The Pile)

Max Activating Token Index: 857

Text #11

Max Range: 0.8292. Min Range: -0.8292

Max Act: 0.5657. Min Act: -0.0000

Data Index: 529986 (The Pile)

Max Activating Token Index: 865

Text #12

Max Range: 0.8292. Min Range: -0.8292

Max Act: 0.4985. Min Act: -0.0000

Data Index: 1794955 (The Pile)

Max Activating Token Index: 301

Text #13

Max Range: 0.8292. Min Range: -0.8292

Max Act: 0.5246. Min Act: -0.0000

Data Index: 1498615 (The Pile)

Max Activating Token Index: 175

Text #14

Max Range: 0.8292. Min Range: -0.8292

Max Act: 0.5248. Min Act: -0.0000

Data Index: 1742629 (The Pile)

Max Activating Token Index: 588

Text #15

Max Range: 0.8292. Min Range: -0.8292

Max Act: 0.3926. Min Act: -0.0000

Data Index: 686861 (The Pile)

Max Activating Token Index: 714

Text #16

Max Range: 0.8292. Min Range: -0.8292

Max Act: 0.4677. Min Act: -0.0000

Data Index: 296139 (The Pile)

Max Activating Token Index: 212

Text #17

Max Range: 0.8292. Min Range: -0.8292

Max Act: 0.5168. Min Act: -0.0000

Data Index: 11315 (The Pile)

Max Activating Token Index: 847

Text #18

Max Range: 0.8292. Min Range: -0.8292

Max Act: 0.4673. Min Act: -0.0000

Data Index: 187020 (The Pile)

Max Activating Token Index: 164

Text #19

Max Range: 0.8292. Min Range: -0.8292

Max Act: 0.4881. Min Act: 0.0000

Data Index: 1099122 (The Pile)

Max Activating Token Index: 228