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

Dataset: The Pile

Neuron 2058 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: 1.0465. Min Range: -1.0465

Max Act: 1.0465. Min Act: -0.0000

Data Index: 1848311 (The Pile)

Max Activating Token Index: 379

Text #1

Max Range: 1.0465. Min Range: -1.0465

Max Act: 0.7855. Min Act: 0.0000

Data Index: 1141956 (The Pile)

Max Activating Token Index: 334

Text #2

Max Range: 1.0465. Min Range: -1.0465

Max Act: 0.7429. Min Act: -0.0000

Data Index: 696458 (The Pile)

Max Activating Token Index: 938

Text #3

Max Range: 1.0465. Min Range: -1.0465

Max Act: 0.6663. Min Act: -0.0000

Data Index: 377185 (The Pile)

Max Activating Token Index: 86

Text #4

Max Range: 1.0465. Min Range: -1.0465

Max Act: 0.5948. Min Act: -0.0000

Data Index: 1034566 (The Pile)

Max Activating Token Index: 313

Text #5

Max Range: 1.0465. Min Range: -1.0465

Max Act: 0.5945. Min Act: -0.0000

Data Index: 1398881 (The Pile)

Max Activating Token Index: 167

Text #6

Max Range: 1.0465. Min Range: -1.0465

Max Act: 0.5501. Min Act: -0.0000

Data Index: 1286269 (The Pile)

Max Activating Token Index: 813

Text #7

Max Range: 1.0465. Min Range: -1.0465

Max Act: 0.5678. Min Act: 0.0000

Data Index: 439252 (The Pile)

Max Activating Token Index: 140

Text #8

Max Range: 1.0465. Min Range: -1.0465

Max Act: 0.5429. Min Act: -0.0000

Data Index: 1294325 (The Pile)

Max Activating Token Index: 185

Text #9

Max Range: 1.0465. Min Range: -1.0465

Max Act: 0.5410. Min Act: -0.0000

Data Index: 166950 (The Pile)

Max Activating Token Index: 40

Text #10

Max Range: 1.0465. Min Range: -1.0465

Max Act: 0.5609. Min Act: 0.0000

Data Index: 1602770 (The Pile)

Max Activating Token Index: 166

Text #11

Max Range: 1.0465. Min Range: -1.0465

Max Act: 0.5423. Min Act: 0.0000

Data Index: 1946065 (The Pile)

Max Activating Token Index: 511

Text #12

Max Range: 1.0465. Min Range: -1.0465

Max Act: 0.5232. Min Act: -0.0000

Data Index: 1126471 (The Pile)

Max Activating Token Index: 369

Text #13

Max Range: 1.0465. Min Range: -1.0465

Max Act: 0.5324. Min Act: -0.0000

Data Index: 276020 (The Pile)

Max Activating Token Index: 268

Text #14

Max Range: 1.0465. Min Range: -1.0465

Max Act: 0.5285. Min Act: 0.0000

Data Index: 1692812 (The Pile)

Max Activating Token Index: 119

Text #15

Max Range: 1.0465. Min Range: -1.0465

Max Act: 0.5308. Min Act: -0.0000

Data Index: 1791052 (The Pile)

Max Activating Token Index: 931

Text #16

Max Range: 1.0465. Min Range: -1.0465

Max Act: 0.4928. Min Act: -0.0000

Data Index: 1035104 (The Pile)

Max Activating Token Index: 681

Text #17

Max Range: 1.0465. Min Range: -1.0465

Max Act: 0.5084. Min Act: 0.0001

Data Index: 1485332 (The Pile)

Max Activating Token Index: 676

Text #18

Max Range: 1.0465. Min Range: -1.0465

Max Act: 0.5210. Min Act: -0.0000

Data Index: 1557189 (The Pile)

Max Activating Token Index: 413

Text #19

Max Range: 1.0465. Min Range: -1.0465

Max Act: 0.4869. Min Act: -0.0000

Data Index: 1304872 (The Pile)

Max Activating Token Index: 17