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

Dataset: The Pile

Neuron 2118 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: 1.9087. Min Range: -1.9087

Max Act: 1.9087. Min Act: -0.0000

Data Index: 846201 (The Pile)

Max Activating Token Index: 355

Text #1

Max Range: 1.9087. Min Range: -1.9087

Max Act: 1.9025. Min Act: -0.0000

Data Index: 929259 (The Pile)

Max Activating Token Index: 197

Text #2

Max Range: 1.9087. Min Range: -1.9087

Max Act: 1.8154. Min Act: -0.0000

Data Index: 371147 (The Pile)

Max Activating Token Index: 588

Text #3

Max Range: 1.9087. Min Range: -1.9087

Max Act: 1.6687. Min Act: -0.0000

Data Index: 1914864 (The Pile)

Max Activating Token Index: 272

Text #4

Max Range: 1.9087. Min Range: -1.9087

Max Act: 1.6459. Min Act: -0.0000

Data Index: 918574 (The Pile)

Max Activating Token Index: 225

Text #5

Max Range: 1.9087. Min Range: -1.9087

Max Act: 1.5908. Min Act: -0.0000

Data Index: 489867 (The Pile)

Max Activating Token Index: 598

Text #6

Max Range: 1.9087. Min Range: -1.9087

Max Act: 1.6782. Min Act: -0.0000

Data Index: 1500082 (The Pile)

Max Activating Token Index: 121

Text #7

Max Range: 1.9087. Min Range: -1.9087

Max Act: 1.4933. Min Act: -0.0000

Data Index: 841410 (The Pile)

Max Activating Token Index: 858

Text #8

Max Range: 1.9087. Min Range: -1.9087

Max Act: 1.6121. Min Act: -0.0000

Data Index: 1405883 (The Pile)

Max Activating Token Index: 187

Text #9

Max Range: 1.9087. Min Range: -1.9087

Max Act: 1.6258. Min Act: -0.0000

Data Index: 282590 (The Pile)

Max Activating Token Index: 157

Text #10

Max Range: 1.9087. Min Range: -1.9087

Max Act: 1.6139. Min Act: -0.0000

Data Index: 1924969 (The Pile)

Max Activating Token Index: 798

Text #11

Max Range: 1.9087. Min Range: -1.9087

Max Act: 1.5165. Min Act: -0.0000

Data Index: 1001393 (The Pile)

Max Activating Token Index: 852

Text #12

Max Range: 1.9087. Min Range: -1.9087

Max Act: 1.4867. Min Act: -0.0000

Data Index: 1961944 (The Pile)

Max Activating Token Index: 193

Text #13

Max Range: 1.9087. Min Range: -1.9087

Max Act: 1.5775. Min Act: -0.0000

Data Index: 712054 (The Pile)

Max Activating Token Index: 315

Text #14

Max Range: 1.9087. Min Range: -1.9087

Max Act: 1.5045. Min Act: -0.0000

Data Index: 250384 (The Pile)

Max Activating Token Index: 715

Text #15

Max Range: 1.9087. Min Range: -1.9087

Max Act: 1.4268. Min Act: -0.0000

Data Index: 376385 (The Pile)

Max Activating Token Index: 490

Text #16

Max Range: 1.9087. Min Range: -1.9087

Max Act: 1.4488. Min Act: -0.0000

Data Index: 1193981 (The Pile)

Max Activating Token Index: 465

Text #17

Max Range: 1.9087. Min Range: -1.9087

Max Act: 1.3476. Min Act: -0.0000

Data Index: 1470932 (The Pile)

Max Activating Token Index: 354

Text #18

Max Range: 1.9087. Min Range: -1.9087

Max Act: 1.4178. Min Act: -0.0000

Data Index: 1905442 (The Pile)

Max Activating Token Index: 71

Text #19

Max Range: 1.9087. Min Range: -1.9087

Max Act: 1.4525. Min Act: -0.0000

Data Index: 1489888 (The Pile)

Max Activating Token Index: 465