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

Dataset: The Pile

Neuron 2592 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: 1.5143. Min Range: -1.5143

Max Act: 1.5143. Min Act: -0.0000

Data Index: 1599250 (The Pile)

Max Activating Token Index: 992

Text #1

Max Range: 1.5143. Min Range: -1.5143

Max Act: 1.2613. Min Act: -0.0000

Data Index: 1041662 (The Pile)

Max Activating Token Index: 751

Text #2

Max Range: 1.5143. Min Range: -1.5143

Max Act: 1.3170. Min Act: -0.0000

Data Index: 1144471 (The Pile)

Max Activating Token Index: 852

Text #3

Max Range: 1.5143. Min Range: -1.5143

Max Act: 1.1909. Min Act: -0.0000

Data Index: 101371 (The Pile)

Max Activating Token Index: 591

Text #4

Max Range: 1.5143. Min Range: -1.5143

Max Act: 1.1715. Min Act: -0.0000

Data Index: 1747758 (The Pile)

Max Activating Token Index: 168

Text #5

Max Range: 1.5143. Min Range: -1.5143

Max Act: 1.1695. Min Act: -0.0000

Data Index: 184531 (The Pile)

Max Activating Token Index: 813

Text #6

Max Range: 1.5143. Min Range: -1.5143

Max Act: 1.1648. Min Act: -0.0000

Data Index: 1839745 (The Pile)

Max Activating Token Index: 104

Text #7

Max Range: 1.5143. Min Range: -1.5143

Max Act: 1.0509. Min Act: -0.0000

Data Index: 1013507 (The Pile)

Max Activating Token Index: 495

Text #8

Max Range: 1.5143. Min Range: -1.5143

Max Act: 1.0382. Min Act: -0.0000

Data Index: 1716805 (The Pile)

Max Activating Token Index: 690

Text #9

Max Range: 1.5143. Min Range: -1.5143

Max Act: 1.0287. Min Act: -0.0000

Data Index: 1037765 (The Pile)

Max Activating Token Index: 683

Text #10

Max Range: 1.5143. Min Range: -1.5143

Max Act: 1.0229. Min Act: -0.0000

Data Index: 188637 (The Pile)

Max Activating Token Index: 508

Text #11

Max Range: 1.5143. Min Range: -1.5143

Max Act: 0.9840. Min Act: -0.0000

Data Index: 1167429 (The Pile)

Max Activating Token Index: 165

Text #12

Max Range: 1.5143. Min Range: -1.5143

Max Act: 0.9474. Min Act: -0.0000

Data Index: 498297 (The Pile)

Max Activating Token Index: 677

Text #13

Max Range: 1.5143. Min Range: -1.5143

Max Act: 0.9233. Min Act: -0.0000

Data Index: 596634 (The Pile)

Max Activating Token Index: 235

Text #14

Max Range: 1.5143. Min Range: -1.5143

Max Act: 0.8520. Min Act: -0.0000

Data Index: 969071 (The Pile)

Max Activating Token Index: 722

Text #15

Max Range: 1.5143. Min Range: -1.5143

Max Act: 0.8200. Min Act: -0.0000

Data Index: 1475258 (The Pile)

Max Activating Token Index: 661

Text #16

Max Range: 1.5143. Min Range: -1.5143

Max Act: 0.8571. Min Act: -0.0000

Data Index: 1267036 (The Pile)

Max Activating Token Index: 690

Text #17

Max Range: 1.5143. Min Range: -1.5143

Max Act: 0.9011. Min Act: -0.0000

Data Index: 1206191 (The Pile)

Max Activating Token Index: 1005

Text #18

Max Range: 1.5143. Min Range: -1.5143

Max Act: 0.8282. Min Act: -0.0000

Data Index: 1482942 (The Pile)

Max Activating Token Index: 489

Text #19

Max Range: 1.5143. Min Range: -1.5143

Max Act: 0.8189. Min Act: 0.0000

Data Index: 1201331 (The Pile)

Max Activating Token Index: 962