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

Dataset: The Pile

Neuron 4512 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4748. Min Range: -0.4748

Max Act: 0.4748. Min Act: -0.0000

Data Index: 243328 (The Pile)

Max Activating Token Index: 503

Text #1

Max Range: 0.4748. Min Range: -0.4748

Max Act: 0.4101. Min Act: -0.0000

Data Index: 303526 (The Pile)

Max Activating Token Index: 246

Text #2

Max Range: 0.4748. Min Range: -0.4748

Max Act: 0.3840. Min Act: -0.0000

Data Index: 105399 (The Pile)

Max Activating Token Index: 215

Text #3

Max Range: 0.4748. Min Range: -0.4748

Max Act: 0.3698. Min Act: -0.0000

Data Index: 1447890 (The Pile)

Max Activating Token Index: 333

Text #4

Max Range: 0.4748. Min Range: -0.4748

Max Act: 0.4198. Min Act: -0.0000

Data Index: 1609330 (The Pile)

Max Activating Token Index: 16

Text #5

Max Range: 0.4748. Min Range: -0.4748

Max Act: 0.3904. Min Act: -0.0000

Data Index: 909805 (The Pile)

Max Activating Token Index: 207

Text #6

Max Range: 0.4748. Min Range: -0.4748

Max Act: 0.3867. Min Act: -0.0000

Data Index: 683017 (The Pile)

Max Activating Token Index: 105

Text #7

Max Range: 0.4748. Min Range: -0.4748

Max Act: 0.3835. Min Act: -0.0000

Data Index: 1225042 (The Pile)

Max Activating Token Index: 673

Text #8

Max Range: 0.4748. Min Range: -0.4748

Max Act: 0.3667. Min Act: -0.0000

Data Index: 537274 (The Pile)

Max Activating Token Index: 477

Text #9

Max Range: 0.4748. Min Range: -0.4748

Max Act: 0.3859. Min Act: -0.0000

Data Index: 1854861 (The Pile)

Max Activating Token Index: 192

Text #10

Max Range: 0.4748. Min Range: -0.4748

Max Act: 0.3904. Min Act: -0.0000

Data Index: 885859 (The Pile)

Max Activating Token Index: 19

Text #11

Max Range: 0.4748. Min Range: -0.4748

Max Act: 0.3999. Min Act: -0.0000

Data Index: 69156 (The Pile)

Max Activating Token Index: 494

Text #12

Max Range: 0.4748. Min Range: -0.4748

Max Act: 0.3552. Min Act: -0.0000

Data Index: 1345611 (The Pile)

Max Activating Token Index: 143

Text #13

Max Range: 0.4748. Min Range: -0.4748

Max Act: 0.3648. Min Act: -0.0000

Data Index: 1990266 (The Pile)

Max Activating Token Index: 163

Text #14

Max Range: 0.4748. Min Range: -0.4748

Max Act: 0.4117. Min Act: -0.0000

Data Index: 1832072 (The Pile)

Max Activating Token Index: 404

Text #15

Max Range: 0.4748. Min Range: -0.4748

Max Act: 0.4250. Min Act: -0.0000

Data Index: 1842363 (The Pile)

Max Activating Token Index: 161

Text #16

Max Range: 0.4748. Min Range: -0.4748

Max Act: 0.3384. Min Act: -0.0000

Data Index: 223087 (The Pile)

Max Activating Token Index: 302

Text #17

Max Range: 0.4748. Min Range: -0.4748

Max Act: 0.3896. Min Act: -0.0000

Data Index: 1022251 (The Pile)

Max Activating Token Index: 801

Text #18

Max Range: 0.4748. Min Range: -0.4748

Max Act: 0.3661. Min Act: -0.0000

Data Index: 474718 (The Pile)

Max Activating Token Index: 290

Text #19

Max Range: 0.4748. Min Range: -0.4748

Max Act: 0.3236. Min Act: -0.0000

Data Index: 1076470 (The Pile)

Max Activating Token Index: 738