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

Dataset: The Pile

Neuron 547 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: 0.7532. Min Range: -0.7532

Max Act: 0.7532. Min Act: -0.0000

Data Index: 190002 (The Pile)

Max Activating Token Index: 484

Text #1

Max Range: 0.7532. Min Range: -0.7532

Max Act: 0.7116. Min Act: -0.0000

Data Index: 1055527 (The Pile)

Max Activating Token Index: 995

Text #2

Max Range: 0.7532. Min Range: -0.7532

Max Act: 0.6096. Min Act: -0.0000

Data Index: 293642 (The Pile)

Max Activating Token Index: 179

Text #3

Max Range: 0.7532. Min Range: -0.7532

Max Act: 0.5858. Min Act: -0.0000

Data Index: 1288387 (The Pile)

Max Activating Token Index: 518

Text #4

Max Range: 0.7532. Min Range: -0.7532

Max Act: 0.5593. Min Act: -0.0000

Data Index: 1484655 (The Pile)

Max Activating Token Index: 233

Text #5

Max Range: 0.7532. Min Range: -0.7532

Max Act: 0.5400. Min Act: -0.0000

Data Index: 746590 (The Pile)

Max Activating Token Index: 799

Text #6

Max Range: 0.7532. Min Range: -0.7532

Max Act: 0.5164. Min Act: -0.0000

Data Index: 1848905 (The Pile)

Max Activating Token Index: 1000

Text #7

Max Range: 0.7532. Min Range: -0.7532

Max Act: 0.5450. Min Act: -0.0000

Data Index: 313436 (The Pile)

Max Activating Token Index: 125

Text #8

Max Range: 0.7532. Min Range: -0.7532

Max Act: 0.5291. Min Act: -0.0000

Data Index: 1696303 (The Pile)

Max Activating Token Index: 273

Text #9

Max Range: 0.7532. Min Range: -0.7532

Max Act: 0.4723. Min Act: -0.0000

Data Index: 834583 (The Pile)

Max Activating Token Index: 759

Text #10

Max Range: 0.7532. Min Range: -0.7532

Max Act: 0.5181. Min Act: -0.0000

Data Index: 992611 (The Pile)

Max Activating Token Index: 29

Text #11

Max Range: 0.7532. Min Range: -0.7532

Max Act: 0.5016. Min Act: -0.0000

Data Index: 98799 (The Pile)

Max Activating Token Index: 413

Text #12

Max Range: 0.7532. Min Range: -0.7532

Max Act: 0.4931. Min Act: -0.0000

Data Index: 10987 (The Pile)

Max Activating Token Index: 680

Text #13

Max Range: 0.7532. Min Range: -0.7532

Max Act: 0.4858. Min Act: -0.0000

Data Index: 978127 (The Pile)

Max Activating Token Index: 895

Text #14

Max Range: 0.7532. Min Range: -0.7532

Max Act: 0.4538. Min Act: -0.0000

Data Index: 1067343 (The Pile)

Max Activating Token Index: 375

Text #15

Max Range: 0.7532. Min Range: -0.7532

Max Act: 0.4718. Min Act: -0.0000

Data Index: 1505811 (The Pile)

Max Activating Token Index: 795

Text #16

Max Range: 0.7532. Min Range: -0.7532

Max Act: 0.4389. Min Act: -0.0000

Data Index: 1508275 (The Pile)

Max Activating Token Index: 910

Text #17

Max Range: 0.7532. Min Range: -0.7532

Max Act: 0.4529. Min Act: -0.0000

Data Index: 109576 (The Pile)

Max Activating Token Index: 890

Text #18

Max Range: 0.7532. Min Range: -0.7532

Max Act: 0.4499. Min Act: -0.0000

Data Index: 1020543 (The Pile)

Max Activating Token Index: 198

Text #19

Max Range: 0.7532. Min Range: -0.7532

Max Act: 0.4298. Min Act: -0.0000

Data Index: 1063662 (The Pile)

Max Activating Token Index: 597