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

Dataset: The Pile

Neuron 4507 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8280. Min Range: -0.8280

Max Act: 0.8280. Min Act: -0.0000

Data Index: 1071459 (The Pile)

Max Activating Token Index: 990

Text #1

Max Range: 0.8280. Min Range: -0.8280

Max Act: 0.5822. Min Act: -0.0000

Data Index: 773219 (The Pile)

Max Activating Token Index: 761

Text #2

Max Range: 0.8280. Min Range: -0.8280

Max Act: 0.5751. Min Act: -0.0000

Data Index: 434031 (The Pile)

Max Activating Token Index: 943

Text #3

Max Range: 0.8280. Min Range: -0.8280

Max Act: 0.5480. Min Act: -0.0000

Data Index: 1311071 (The Pile)

Max Activating Token Index: 881

Text #4

Max Range: 0.8280. Min Range: -0.8280

Max Act: 0.5456. Min Act: -0.0000

Data Index: 1803130 (The Pile)

Max Activating Token Index: 688

Text #5

Max Range: 0.8280. Min Range: -0.8280

Max Act: 0.5010. Min Act: -0.0000

Data Index: 22025 (The Pile)

Max Activating Token Index: 949

Text #6

Max Range: 0.8280. Min Range: -0.8280

Max Act: 0.5456. Min Act: -0.0000

Data Index: 236596 (The Pile)

Max Activating Token Index: 1021

Text #7

Max Range: 0.8280. Min Range: -0.8280

Max Act: 0.5073. Min Act: -0.0000

Data Index: 1104921 (The Pile)

Max Activating Token Index: 825

Text #8

Max Range: 0.8280. Min Range: -0.8280

Max Act: 0.5001. Min Act: -0.0000

Data Index: 1266319 (The Pile)

Max Activating Token Index: 860

Text #9

Max Range: 0.8280. Min Range: -0.8280

Max Act: 0.4502. Min Act: -0.0000

Data Index: 1870178 (The Pile)

Max Activating Token Index: 128

Text #10

Max Range: 0.8280. Min Range: -0.8280

Max Act: 0.4511. Min Act: -0.0000

Data Index: 330788 (The Pile)

Max Activating Token Index: 865

Text #11

Max Range: 0.8280. Min Range: -0.8280

Max Act: 0.4480. Min Act: -0.0000

Data Index: 1329545 (The Pile)

Max Activating Token Index: 262

Text #12

Max Range: 0.8280. Min Range: -0.8280

Max Act: 0.4498. Min Act: -0.0000

Data Index: 1696591 (The Pile)

Max Activating Token Index: 629

Text #13

Max Range: 0.8280. Min Range: -0.8280

Max Act: 0.4559. Min Act: -0.0000

Data Index: 1345309 (The Pile)

Max Activating Token Index: 891

Text #14

Max Range: 0.8280. Min Range: -0.8280

Max Act: 0.4313. Min Act: -0.0000

Data Index: 1243895 (The Pile)

Max Activating Token Index: 868

Text #15

Max Range: 0.8280. Min Range: -0.8280

Max Act: 0.4042. Min Act: -0.0000

Data Index: 451409 (The Pile)

Max Activating Token Index: 543

Text #16

Max Range: 0.8280. Min Range: -0.8280

Max Act: 0.4142. Min Act: -0.0000

Data Index: 361467 (The Pile)

Max Activating Token Index: 837

Text #17

Max Range: 0.8280. Min Range: -0.8280

Max Act: 0.4019. Min Act: -0.0000

Data Index: 241804 (The Pile)

Max Activating Token Index: 999

Text #18

Max Range: 0.8280. Min Range: -0.8280

Max Act: 0.4036. Min Act: -0.0000

Data Index: 340582 (The Pile)

Max Activating Token Index: 582

Text #19

Max Range: 0.8280. Min Range: -0.8280

Max Act: 0.4066. Min Act: -0.0000

Data Index: 826651 (The Pile)

Max Activating Token Index: 513