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

Dataset: The Pile

Neuron 3996 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9795. Min Range: -0.9795

Max Act: 0.9795. Min Act: -0.0000

Data Index: 1146113 (The Pile)

Max Activating Token Index: 876

Text #1

Max Range: 0.9795. Min Range: -0.9795

Max Act: 0.8062. Min Act: -0.0000

Data Index: 1686871 (The Pile)

Max Activating Token Index: 21

Text #2

Max Range: 0.9795. Min Range: -0.9795

Max Act: 0.6424. Min Act: -0.0000

Data Index: 32009 (The Pile)

Max Activating Token Index: 1000

Text #3

Max Range: 0.9795. Min Range: -0.9795

Max Act: 0.6377. Min Act: -0.0000

Data Index: 631690 (The Pile)

Max Activating Token Index: 802

Text #4

Max Range: 0.9795. Min Range: -0.9795

Max Act: 0.6519. Min Act: -0.0000

Data Index: 1247007 (The Pile)

Max Activating Token Index: 198

Text #5

Max Range: 0.9795. Min Range: -0.9795

Max Act: 0.6287. Min Act: -0.0000

Data Index: 368550 (The Pile)

Max Activating Token Index: 295

Text #6

Max Range: 0.9795. Min Range: -0.9795

Max Act: 0.5890. Min Act: -0.0000

Data Index: 1334857 (The Pile)

Max Activating Token Index: 512

Text #7

Max Range: 0.9795. Min Range: -0.9795

Max Act: 0.5222. Min Act: -0.0000

Data Index: 1503822 (The Pile)

Max Activating Token Index: 873

Text #8

Max Range: 0.9795. Min Range: -0.9795

Max Act: 0.5789. Min Act: -0.0000

Data Index: 1759822 (The Pile)

Max Activating Token Index: 267

Text #9

Max Range: 0.9795. Min Range: -0.9795

Max Act: 0.5612. Min Act: -0.0000

Data Index: 171406 (The Pile)

Max Activating Token Index: 254

Text #10

Max Range: 0.9795. Min Range: -0.9795

Max Act: 0.5564. Min Act: -0.0000

Data Index: 499971 (The Pile)

Max Activating Token Index: 733

Text #11

Max Range: 0.9795. Min Range: -0.9795

Max Act: 0.5731. Min Act: -0.0000

Data Index: 504035 (The Pile)

Max Activating Token Index: 498

Text #12

Max Range: 0.9795. Min Range: -0.9795

Max Act: 0.5621. Min Act: -0.0000

Data Index: 442516 (The Pile)

Max Activating Token Index: 850

Text #13

Max Range: 0.9795. Min Range: -0.9795

Max Act: 0.5343. Min Act: -0.0000

Data Index: 397111 (The Pile)

Max Activating Token Index: 144

Text #14

Max Range: 0.9795. Min Range: -0.9795

Max Act: 0.5469. Min Act: -0.0000

Data Index: 894906 (The Pile)

Max Activating Token Index: 219

Text #15

Max Range: 0.9795. Min Range: -0.9795

Max Act: 0.5358. Min Act: -0.0000

Data Index: 769849 (The Pile)

Max Activating Token Index: 168

Text #16

Max Range: 0.9795. Min Range: -0.9795

Max Act: 0.5462. Min Act: -0.0000

Data Index: 691911 (The Pile)

Max Activating Token Index: 422

Text #17

Max Range: 0.9795. Min Range: -0.9795

Max Act: 0.5396. Min Act: -0.0000

Data Index: 828121 (The Pile)

Max Activating Token Index: 903

Text #18

Max Range: 0.9795. Min Range: -0.9795

Max Act: 0.5450. Min Act: -0.0000

Data Index: 1208660 (The Pile)

Max Activating Token Index: 974

Text #19

Max Range: 0.9795. Min Range: -0.9795

Max Act: 0.5418. Min Act: -0.0000

Data Index: 912639 (The Pile)

Max Activating Token Index: 243