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

Dataset: The Pile

Neuron 1302 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: 0.6000. Min Range: -0.6000

Max Act: 0.5417. Min Act: -0.0000

Data Index: 1176169 (The Pile)

Max Activating Token Index: 305

Text #1

Max Range: 0.6000. Min Range: -0.6000

Max Act: 0.5893. Min Act: -0.0000

Data Index: 982899 (The Pile)

Max Activating Token Index: 640

Text #2

Max Range: 0.6000. Min Range: -0.6000

Max Act: 0.5126. Min Act: -0.0000

Data Index: 765590 (The Pile)

Max Activating Token Index: 590

Text #3

Max Range: 0.6000. Min Range: -0.6000

Max Act: 0.6000. Min Act: -0.0000

Data Index: 1141553 (The Pile)

Max Activating Token Index: 368

Text #4

Max Range: 0.6000. Min Range: -0.6000

Max Act: 0.5934. Min Act: -0.0000

Data Index: 1747039 (The Pile)

Max Activating Token Index: 778

Text #5

Max Range: 0.6000. Min Range: -0.6000

Max Act: 0.5526. Min Act: -0.0000

Data Index: 1435014 (The Pile)

Max Activating Token Index: 634

Text #6

Max Range: 0.6000. Min Range: -0.6000

Max Act: 0.4816. Min Act: 0.0000

Data Index: 1295254 (The Pile)

Max Activating Token Index: 355

Text #7

Max Range: 0.6000. Min Range: -0.6000

Max Act: 0.5633. Min Act: -0.0000

Data Index: 916357 (The Pile)

Max Activating Token Index: 737

Text #8

Max Range: 0.6000. Min Range: -0.6000

Max Act: 0.4651. Min Act: 0.0000

Data Index: 283626 (The Pile)

Max Activating Token Index: 655

Text #9

Max Range: 0.6000. Min Range: -0.6000

Max Act: 0.4500. Min Act: -0.0000

Data Index: 1368562 (The Pile)

Max Activating Token Index: 55

Text #10

Max Range: 0.6000. Min Range: -0.6000

Max Act: 0.4271. Min Act: -0.0000

Data Index: 473060 (The Pile)

Max Activating Token Index: 518

Text #11

Max Range: 0.6000. Min Range: -0.6000

Max Act: 0.3693. Min Act: -0.0000

Data Index: 781950 (The Pile)

Max Activating Token Index: 291

Text #12

Max Range: 0.6000. Min Range: -0.6000

Max Act: 0.4018. Min Act: -0.0000

Data Index: 1747428 (The Pile)

Max Activating Token Index: 854

Text #13

Max Range: 0.6000. Min Range: -0.6000

Max Act: 0.2967. Min Act: -0.0000

Data Index: 1298250 (The Pile)

Max Activating Token Index: 774

Text #14

Max Range: 0.6000. Min Range: -0.6000

Max Act: 0.3565. Min Act: -0.0000

Data Index: 623786 (The Pile)

Max Activating Token Index: 291

Text #15

Max Range: 0.6000. Min Range: -0.6000

Max Act: 0.3192. Min Act: -0.0000

Data Index: 472807 (The Pile)

Max Activating Token Index: 772

Text #16

Max Range: 0.6000. Min Range: -0.6000

Max Act: 0.3323. Min Act: -0.0000

Data Index: 1436926 (The Pile)

Max Activating Token Index: 931

Text #17

Max Range: 0.6000. Min Range: -0.6000

Max Act: 0.3289. Min Act: 0.0000

Data Index: 1832940 (The Pile)

Max Activating Token Index: 528

Text #18

Max Range: 0.6000. Min Range: -0.6000

Max Act: 0.3458. Min Act: -0.0000

Data Index: 1149155 (The Pile)

Max Activating Token Index: 899

Text #19

Max Range: 0.6000. Min Range: -0.6000

Max Act: 0.3202. Min Act: -0.0000

Data Index: 1684617 (The Pile)

Max Activating Token Index: 630