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

Dataset: The Pile

Neuron 1495 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.6278. Min Range: -0.6278

Max Act: 0.6278. Min Act: -0.0000

Data Index: 948648 (The Pile)

Max Activating Token Index: 40

Text #1

Max Range: 0.6278. Min Range: -0.6278

Max Act: 0.5378. Min Act: -0.0000

Data Index: 140333 (The Pile)

Max Activating Token Index: 153

Text #2

Max Range: 0.6278. Min Range: -0.6278

Max Act: 0.4575. Min Act: -0.0000

Data Index: 1975380 (The Pile)

Max Activating Token Index: 155

Text #3

Max Range: 0.6278. Min Range: -0.6278

Max Act: 0.4856. Min Act: -0.0000

Data Index: 1557589 (The Pile)

Max Activating Token Index: 467

Text #4

Max Range: 0.6278. Min Range: -0.6278

Max Act: 0.4739. Min Act: -0.0000

Data Index: 1989805 (The Pile)

Max Activating Token Index: 624

Text #5

Max Range: 0.6278. Min Range: -0.6278

Max Act: 0.4986. Min Act: -0.0000

Data Index: 954531 (The Pile)

Max Activating Token Index: 891

Text #6

Max Range: 0.6278. Min Range: -0.6278

Max Act: 0.4678. Min Act: -0.0000

Data Index: 1242572 (The Pile)

Max Activating Token Index: 18

Text #7

Max Range: 0.6278. Min Range: -0.6278

Max Act: 0.4743. Min Act: -0.0000

Data Index: 364009 (The Pile)

Max Activating Token Index: 175

Text #8

Max Range: 0.6278. Min Range: -0.6278

Max Act: 0.5145. Min Act: -0.0000

Data Index: 388443 (The Pile)

Max Activating Token Index: 744

Text #9

Max Range: 0.6278. Min Range: -0.6278

Max Act: 0.4572. Min Act: -0.0000

Data Index: 377442 (The Pile)

Max Activating Token Index: 915

Text #10

Max Range: 0.6278. Min Range: -0.6278

Max Act: 0.4878. Min Act: -0.0000

Data Index: 1071242 (The Pile)

Max Activating Token Index: 905

Text #11

Max Range: 0.6278. Min Range: -0.6278

Max Act: 0.4439. Min Act: -0.0000

Data Index: 774831 (The Pile)

Max Activating Token Index: 261

Text #12

Max Range: 0.6278. Min Range: -0.6278

Max Act: 0.4711. Min Act: -0.0000

Data Index: 1441873 (The Pile)

Max Activating Token Index: 880

Text #13

Max Range: 0.6278. Min Range: -0.6278

Max Act: 0.4592. Min Act: -0.0000

Data Index: 380337 (The Pile)

Max Activating Token Index: 837

Text #14

Max Range: 0.6278. Min Range: -0.6278

Max Act: 0.4575. Min Act: -0.0000

Data Index: 1577106 (The Pile)

Max Activating Token Index: 453

Text #15

Max Range: 0.6278. Min Range: -0.6278

Max Act: 0.4355. Min Act: -0.0000

Data Index: 1517165 (The Pile)

Max Activating Token Index: 263

Text #16

Max Range: 0.6278. Min Range: -0.6278

Max Act: 0.4236. Min Act: -0.0000

Data Index: 1677528 (The Pile)

Max Activating Token Index: 685

Text #17

Max Range: 0.6278. Min Range: -0.6278

Max Act: 0.4295. Min Act: -0.0000

Data Index: 147286 (The Pile)

Max Activating Token Index: 938

Text #18

Max Range: 0.6278. Min Range: -0.6278

Max Act: 0.4737. Min Act: -0.0000

Data Index: 75362 (The Pile)

Max Activating Token Index: 856

Text #19

Max Range: 0.6278. Min Range: -0.6278

Max Act: 0.4886. Min Act: -0.0000

Data Index: 1796140 (The Pile)

Max Activating Token Index: 834