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

Dataset: The Pile

Neuron 3385 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: 0.7154. Min Range: -0.7154

Max Act: 0.7154. Min Act: -0.0000

Data Index: 656129 (The Pile)

Max Activating Token Index: 444

Text #1

Max Range: 0.7154. Min Range: -0.7154

Max Act: 0.5499. Min Act: -0.0000

Data Index: 1175639 (The Pile)

Max Activating Token Index: 858

Text #2

Max Range: 0.7154. Min Range: -0.7154

Max Act: 0.5063. Min Act: -0.0000

Data Index: 1679499 (The Pile)

Max Activating Token Index: 731

Text #3

Max Range: 0.7154. Min Range: -0.7154

Max Act: 0.5083. Min Act: -0.0000

Data Index: 294842 (The Pile)

Max Activating Token Index: 98

Text #4

Max Range: 0.7154. Min Range: -0.7154

Max Act: 0.4543. Min Act: -0.0000

Data Index: 539883 (The Pile)

Max Activating Token Index: 507

Text #5

Max Range: 0.7154. Min Range: -0.7154

Max Act: 0.4776. Min Act: -0.0000

Data Index: 1887971 (The Pile)

Max Activating Token Index: 879

Text #6

Max Range: 0.7154. Min Range: -0.7154

Max Act: 0.5047. Min Act: -0.0000

Data Index: 1751513 (The Pile)

Max Activating Token Index: 160

Text #7

Max Range: 0.7154. Min Range: -0.7154

Max Act: 0.4891. Min Act: -0.0000

Data Index: 1914627 (The Pile)

Max Activating Token Index: 141

Text #8

Max Range: 0.7154. Min Range: -0.7154

Max Act: 0.4671. Min Act: -0.0000

Data Index: 558163 (The Pile)

Max Activating Token Index: 126

Text #9

Max Range: 0.7154. Min Range: -0.7154

Max Act: 0.4355. Min Act: -0.0000

Data Index: 885462 (The Pile)

Max Activating Token Index: 460

Text #10

Max Range: 0.7154. Min Range: -0.7154

Max Act: 0.4469. Min Act: -0.0000

Data Index: 1788456 (The Pile)

Max Activating Token Index: 595

Text #11

Max Range: 0.7154. Min Range: -0.7154

Max Act: 0.4875. Min Act: -0.0000

Data Index: 333638 (The Pile)

Max Activating Token Index: 214

Text #12

Max Range: 0.7154. Min Range: -0.7154

Max Act: 0.5011. Min Act: -0.0000

Data Index: 1494436 (The Pile)

Max Activating Token Index: 409

Text #13

Max Range: 0.7154. Min Range: -0.7154

Max Act: 0.4892. Min Act: -0.0000

Data Index: 1101223 (The Pile)

Max Activating Token Index: 409

Text #14

Max Range: 0.7154. Min Range: -0.7154

Max Act: 0.4694. Min Act: -0.0000

Data Index: 697510 (The Pile)

Max Activating Token Index: 250

Text #15

Max Range: 0.7154. Min Range: -0.7154

Max Act: 0.4561. Min Act: -0.0000

Data Index: 417892 (The Pile)

Max Activating Token Index: 708

Text #16

Max Range: 0.7154. Min Range: -0.7154

Max Act: 0.4665. Min Act: -0.0000

Data Index: 106225 (The Pile)

Max Activating Token Index: 237

Text #17

Max Range: 0.7154. Min Range: -0.7154

Max Act: 0.4574. Min Act: -0.0000

Data Index: 1683487 (The Pile)

Max Activating Token Index: 694

Text #18

Max Range: 0.7154. Min Range: -0.7154

Max Act: 0.4847. Min Act: -0.0000

Data Index: 857151 (The Pile)

Max Activating Token Index: 629

Text #19

Max Range: 0.7154. Min Range: -0.7154

Max Act: 0.4395. Min Act: -0.0000

Data Index: 1980095 (The Pile)

Max Activating Token Index: 31