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

Dataset: The Pile

Neuron 4630 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5487. Min Range: -0.5487

Max Act: 0.5487. Min Act: -0.0000

Data Index: 883568 (The Pile)

Max Activating Token Index: 975

Text #1

Max Range: 0.5487. Min Range: -0.5487

Max Act: 0.5450. Min Act: -0.0000

Data Index: 1670774 (The Pile)

Max Activating Token Index: 1002

Text #2

Max Range: 0.5487. Min Range: -0.5487

Max Act: 0.5391. Min Act: -0.0000

Data Index: 1504311 (The Pile)

Max Activating Token Index: 307

Text #3

Max Range: 0.5487. Min Range: -0.5487

Max Act: 0.4908. Min Act: -0.0000

Data Index: 1376646 (The Pile)

Max Activating Token Index: 796

Text #4

Max Range: 0.5487. Min Range: -0.5487

Max Act: 0.5088. Min Act: -0.0000

Data Index: 1683380 (The Pile)

Max Activating Token Index: 595

Text #5

Max Range: 0.5487. Min Range: -0.5487

Max Act: 0.5212. Min Act: -0.0000

Data Index: 1702594 (The Pile)

Max Activating Token Index: 257

Text #6

Max Range: 0.5487. Min Range: -0.5487

Max Act: 0.4787. Min Act: -0.0000

Data Index: 12168 (The Pile)

Max Activating Token Index: 607

Text #7

Max Range: 0.5487. Min Range: -0.5487

Max Act: 0.5080. Min Act: -0.0000

Data Index: 1456198 (The Pile)

Max Activating Token Index: 258

Text #8

Max Range: 0.5487. Min Range: -0.5487

Max Act: 0.4842. Min Act: -0.0000

Data Index: 646576 (The Pile)

Max Activating Token Index: 331

Text #9

Max Range: 0.5487. Min Range: -0.5487

Max Act: 0.5108. Min Act: -0.0000

Data Index: 427080 (The Pile)

Max Activating Token Index: 949

Text #10

Max Range: 0.5487. Min Range: -0.5487

Max Act: 0.5155. Min Act: -0.0000

Data Index: 333976 (The Pile)

Max Activating Token Index: 612

Text #11

Max Range: 0.5487. Min Range: -0.5487

Max Act: 0.4734. Min Act: -0.0000

Data Index: 1502642 (The Pile)

Max Activating Token Index: 287

Text #12

Max Range: 0.5487. Min Range: -0.5487

Max Act: 0.4896. Min Act: -0.0000

Data Index: 1385681 (The Pile)

Max Activating Token Index: 283

Text #13

Max Range: 0.5487. Min Range: -0.5487

Max Act: 0.4802. Min Act: -0.0000

Data Index: 1801791 (The Pile)

Max Activating Token Index: 82

Text #14

Max Range: 0.5487. Min Range: -0.5487

Max Act: 0.4807. Min Act: -0.0000

Data Index: 1200527 (The Pile)

Max Activating Token Index: 788

Text #15

Max Range: 0.5487. Min Range: -0.5487

Max Act: 0.4512. Min Act: -0.0000

Data Index: 1734821 (The Pile)

Max Activating Token Index: 883

Text #16

Max Range: 0.5487. Min Range: -0.5487

Max Act: 0.4444. Min Act: -0.0000

Data Index: 775311 (The Pile)

Max Activating Token Index: 922

Text #17

Max Range: 0.5487. Min Range: -0.5487

Max Act: 0.4524. Min Act: -0.0000

Data Index: 1454643 (The Pile)

Max Activating Token Index: 826

Text #18

Max Range: 0.5487. Min Range: -0.5487

Max Act: 0.4637. Min Act: -0.0000

Data Index: 660420 (The Pile)

Max Activating Token Index: 334

Text #19

Max Range: 0.5487. Min Range: -0.5487

Max Act: 0.4810. Min Act: -0.0000

Data Index: 401395 (The Pile)

Max Activating Token Index: 450