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

Dataset: The Pile

Neuron 2132 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: 0.7148. Min Range: -0.7148

Max Act: 0.6821. Min Act: -0.0000

Data Index: 1985201 (The Pile)

Max Activating Token Index: 859

Text #1

Max Range: 0.7148. Min Range: -0.7148

Max Act: 0.7148. Min Act: -0.0000

Data Index: 1585299 (The Pile)

Max Activating Token Index: 312

Text #2

Max Range: 0.7148. Min Range: -0.7148

Max Act: 0.6259. Min Act: -0.0000

Data Index: 632548 (The Pile)

Max Activating Token Index: 645

Text #3

Max Range: 0.7148. Min Range: -0.7148

Max Act: 0.6224. Min Act: -0.0000

Data Index: 152001 (The Pile)

Max Activating Token Index: 751

Text #4

Max Range: 0.7148. Min Range: -0.7148

Max Act: 0.6769. Min Act: -0.0000

Data Index: 684803 (The Pile)

Max Activating Token Index: 365

Text #5

Max Range: 0.7148. Min Range: -0.7148

Max Act: 0.6624. Min Act: -0.0000

Data Index: 1525952 (The Pile)

Max Activating Token Index: 389

Text #6

Max Range: 0.7148. Min Range: -0.7148

Max Act: 0.6482. Min Act: -0.0000

Data Index: 352316 (The Pile)

Max Activating Token Index: 1008

Text #7

Max Range: 0.7148. Min Range: -0.7148

Max Act: 0.6226. Min Act: -0.0000

Data Index: 1118426 (The Pile)

Max Activating Token Index: 123

Text #8

Max Range: 0.7148. Min Range: -0.7148

Max Act: 0.6271. Min Act: -0.0000

Data Index: 560086 (The Pile)

Max Activating Token Index: 686

Text #9

Max Range: 0.7148. Min Range: -0.7148

Max Act: 0.5771. Min Act: -0.0000

Data Index: 1143994 (The Pile)

Max Activating Token Index: 795

Text #10

Max Range: 0.7148. Min Range: -0.7148

Max Act: 0.6185. Min Act: -0.0000

Data Index: 71265 (The Pile)

Max Activating Token Index: 339

Text #11

Max Range: 0.7148. Min Range: -0.7148

Max Act: 0.5896. Min Act: -0.0000

Data Index: 1625454 (The Pile)

Max Activating Token Index: 638

Text #12

Max Range: 0.7148. Min Range: -0.7148

Max Act: 0.5812. Min Act: -0.0000

Data Index: 1878543 (The Pile)

Max Activating Token Index: 446

Text #13

Max Range: 0.7148. Min Range: -0.7148

Max Act: 0.5744. Min Act: -0.0000

Data Index: 435701 (The Pile)

Max Activating Token Index: 969

Text #14

Max Range: 0.7148. Min Range: -0.7148

Max Act: 0.5405. Min Act: -0.0000

Data Index: 1327189 (The Pile)

Max Activating Token Index: 922

Text #15

Max Range: 0.7148. Min Range: -0.7148

Max Act: 0.5331. Min Act: -0.0000

Data Index: 1625538 (The Pile)

Max Activating Token Index: 841

Text #16

Max Range: 0.7148. Min Range: -0.7148

Max Act: 0.5579. Min Act: -0.0000

Data Index: 251726 (The Pile)

Max Activating Token Index: 316

Text #17

Max Range: 0.7148. Min Range: -0.7148

Max Act: 0.5267. Min Act: -0.0000

Data Index: 1301216 (The Pile)

Max Activating Token Index: 83

Text #18

Max Range: 0.7148. Min Range: -0.7148

Max Act: 0.5635. Min Act: -0.0000

Data Index: 630650 (The Pile)

Max Activating Token Index: 1018

Text #19

Max Range: 0.7148. Min Range: -0.7148

Max Act: 0.5570. Min Act: -0.0000

Data Index: 1877499 (The Pile)

Max Activating Token Index: 586