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

Dataset: The Pile

Neuron 4153 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.4462. Min Range: -1.4462

Max Act: 1.4254. Min Act: -0.0000

Data Index: 445039 (The Pile)

Max Activating Token Index: 183

Text #1

Max Range: 1.4462. Min Range: -1.4462

Max Act: 1.4462. Min Act: -0.0000

Data Index: 348155 (The Pile)

Max Activating Token Index: 167

Text #2

Max Range: 1.4462. Min Range: -1.4462

Max Act: 1.2244. Min Act: -0.0000

Data Index: 408738 (The Pile)

Max Activating Token Index: 20

Text #3

Max Range: 1.4462. Min Range: -1.4462

Max Act: 0.9896. Min Act: -0.0000

Data Index: 1961623 (The Pile)

Max Activating Token Index: 239

Text #4

Max Range: 1.4462. Min Range: -1.4462

Max Act: 0.9703. Min Act: -0.0000

Data Index: 391823 (The Pile)

Max Activating Token Index: 107

Text #5

Max Range: 1.4462. Min Range: -1.4462

Max Act: 1.0619. Min Act: -0.0000

Data Index: 1814176 (The Pile)

Max Activating Token Index: 96

Text #6

Max Range: 1.4462. Min Range: -1.4462

Max Act: 0.9465. Min Act: -0.0000

Data Index: 1305161 (The Pile)

Max Activating Token Index: 89

Text #7

Max Range: 1.4462. Min Range: -1.4462

Max Act: 1.0144. Min Act: -0.0000

Data Index: 984172 (The Pile)

Max Activating Token Index: 281

Text #8

Max Range: 1.4462. Min Range: -1.4462

Max Act: 0.9304. Min Act: -0.0000

Data Index: 701713 (The Pile)

Max Activating Token Index: 102

Text #9

Max Range: 1.4462. Min Range: -1.4462

Max Act: 0.9794. Min Act: -0.0000

Data Index: 1232372 (The Pile)

Max Activating Token Index: 173

Text #10

Max Range: 1.4462. Min Range: -1.4462

Max Act: 0.9172. Min Act: -0.0000

Data Index: 1051392 (The Pile)

Max Activating Token Index: 102

Text #11

Max Range: 1.4462. Min Range: -1.4462

Max Act: 0.9060. Min Act: -0.0000

Data Index: 1632887 (The Pile)

Max Activating Token Index: 8

Text #12

Max Range: 1.4462. Min Range: -1.4462

Max Act: 0.8888. Min Act: -0.0000

Data Index: 1899031 (The Pile)

Max Activating Token Index: 69

Text #13

Max Range: 1.4462. Min Range: -1.4462

Max Act: 0.8707. Min Act: -0.0000

Data Index: 29448 (The Pile)

Max Activating Token Index: 230

Text #14

Max Range: 1.4462. Min Range: -1.4462

Max Act: 0.9576. Min Act: -0.0000

Data Index: 315635 (The Pile)

Max Activating Token Index: 517

Text #15

Max Range: 1.4462. Min Range: -1.4462

Max Act: 0.8894. Min Act: -0.0000

Data Index: 514702 (The Pile)

Max Activating Token Index: 81

Text #16

Max Range: 1.4462. Min Range: -1.4462

Max Act: 0.9162. Min Act: -0.0000

Data Index: 1539716 (The Pile)

Max Activating Token Index: 349

Text #17

Max Range: 1.4462. Min Range: -1.4462

Max Act: 0.8041. Min Act: -0.0000

Data Index: 814823 (The Pile)

Max Activating Token Index: 845

Text #18

Max Range: 1.4462. Min Range: -1.4462

Max Act: 0.8140. Min Act: 0.0000

Data Index: 1964887 (The Pile)

Max Activating Token Index: 73

Text #19

Max Range: 1.4462. Min Range: -1.4462

Max Act: 0.8120. Min Act: -0.0000

Data Index: 1675674 (The Pile)

Max Activating Token Index: 586