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

Dataset: The Pile

Neuron 1992 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9932. Min Range: -0.9932

Max Act: 0.9662. Min Act: -0.0000

Data Index: 474467 (The Pile)

Max Activating Token Index: 686

Text #1

Max Range: 0.9932. Min Range: -0.9932

Max Act: 0.9388. Min Act: -0.0000

Data Index: 1916931 (The Pile)

Max Activating Token Index: 215

Text #2

Max Range: 0.9932. Min Range: -0.9932

Max Act: 0.9932. Min Act: -0.0001

Data Index: 803132 (The Pile)

Max Activating Token Index: 980

Text #3

Max Range: 0.9932. Min Range: -0.9932

Max Act: 0.9319. Min Act: -0.0000

Data Index: 320019 (The Pile)

Max Activating Token Index: 780

Text #4

Max Range: 0.9932. Min Range: -0.9932

Max Act: 0.8966. Min Act: -0.0000

Data Index: 1230298 (The Pile)

Max Activating Token Index: 745

Text #5

Max Range: 0.9932. Min Range: -0.9932

Max Act: 0.8739. Min Act: -0.0000

Data Index: 1314674 (The Pile)

Max Activating Token Index: 999

Text #6

Max Range: 0.9932. Min Range: -0.9932

Max Act: 0.8724. Min Act: -0.0000

Data Index: 1884990 (The Pile)

Max Activating Token Index: 782

Text #7

Max Range: 0.9932. Min Range: -0.9932

Max Act: 0.8601. Min Act: -0.0000

Data Index: 35763 (The Pile)

Max Activating Token Index: 173

Text #8

Max Range: 0.9932. Min Range: -0.9932

Max Act: 0.8932. Min Act: -0.0000

Data Index: 393814 (The Pile)

Max Activating Token Index: 691

Text #9

Max Range: 0.9932. Min Range: -0.9932

Max Act: 0.8595. Min Act: -0.0001

Data Index: 1394561 (The Pile)

Max Activating Token Index: 352

Text #10

Max Range: 0.9932. Min Range: -0.9932

Max Act: 0.8571. Min Act: -0.0000

Data Index: 597851 (The Pile)

Max Activating Token Index: 565

Text #11

Max Range: 0.9932. Min Range: -0.9932

Max Act: 0.8811. Min Act: -0.0000

Data Index: 186350 (The Pile)

Max Activating Token Index: 225

Text #12

Max Range: 0.9932. Min Range: -0.9932

Max Act: 0.8750. Min Act: -0.0000

Data Index: 66889 (The Pile)

Max Activating Token Index: 142

Text #13

Max Range: 0.9932. Min Range: -0.9932

Max Act: 0.9279. Min Act: -0.0000

Data Index: 1446145 (The Pile)

Max Activating Token Index: 994

Text #14

Max Range: 0.9932. Min Range: -0.9932

Max Act: 0.8377. Min Act: -0.0000

Data Index: 1753562 (The Pile)

Max Activating Token Index: 945

Text #15

Max Range: 0.9932. Min Range: -0.9932

Max Act: 0.8056. Min Act: -0.0000

Data Index: 532502 (The Pile)

Max Activating Token Index: 995

Text #16

Max Range: 0.9932. Min Range: -0.9932

Max Act: 0.8641. Min Act: -0.0000

Data Index: 630701 (The Pile)

Max Activating Token Index: 308

Text #17

Max Range: 0.9932. Min Range: -0.9932

Max Act: 0.8617. Min Act: -0.0000

Data Index: 190381 (The Pile)

Max Activating Token Index: 473

Text #18

Max Range: 0.9932. Min Range: -0.9932

Max Act: 0.8636. Min Act: -0.0000

Data Index: 1720516 (The Pile)

Max Activating Token Index: 431

Text #19

Max Range: 0.9932. Min Range: -0.9932

Max Act: 0.8557. Min Act: -0.0000

Data Index: 57482 (The Pile)

Max Activating Token Index: 160