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

Dataset: The Pile

Neuron 1071 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8255. Min Range: -0.8255

Max Act: 0.8255. Min Act: -0.0000

Data Index: 1952621 (The Pile)

Max Activating Token Index: 471

Text #1

Max Range: 0.8255. Min Range: -0.8255

Max Act: 0.7209. Min Act: -0.0000

Data Index: 74494 (The Pile)

Max Activating Token Index: 737

Text #2

Max Range: 0.8255. Min Range: -0.8255

Max Act: 0.7309. Min Act: -0.0000

Data Index: 981028 (The Pile)

Max Activating Token Index: 673

Text #3

Max Range: 0.8255. Min Range: -0.8255

Max Act: 0.6596. Min Act: -0.0000

Data Index: 519297 (The Pile)

Max Activating Token Index: 854

Text #4

Max Range: 0.8255. Min Range: -0.8255

Max Act: 0.6941. Min Act: -0.0000

Data Index: 532899 (The Pile)

Max Activating Token Index: 366

Text #5

Max Range: 0.8255. Min Range: -0.8255

Max Act: 0.6635. Min Act: -0.0000

Data Index: 321298 (The Pile)

Max Activating Token Index: 1020

Text #6

Max Range: 0.8255. Min Range: -0.8255

Max Act: 0.6591. Min Act: -0.0000

Data Index: 972427 (The Pile)

Max Activating Token Index: 504

Text #7

Max Range: 0.8255. Min Range: -0.8255

Max Act: 0.6325. Min Act: -0.0000

Data Index: 410358 (The Pile)

Max Activating Token Index: 700

Text #8

Max Range: 0.8255. Min Range: -0.8255

Max Act: 0.6389. Min Act: -0.0000

Data Index: 1574850 (The Pile)

Max Activating Token Index: 371

Text #9

Max Range: 0.8255. Min Range: -0.8255

Max Act: 0.6175. Min Act: -0.0000

Data Index: 1158674 (The Pile)

Max Activating Token Index: 655

Text #10

Max Range: 0.8255. Min Range: -0.8255

Max Act: 0.6348. Min Act: -0.0000

Data Index: 374658 (The Pile)

Max Activating Token Index: 629

Text #11

Max Range: 0.8255. Min Range: -0.8255

Max Act: 0.6536. Min Act: -0.0000

Data Index: 983983 (The Pile)

Max Activating Token Index: 810

Text #12

Max Range: 0.8255. Min Range: -0.8255

Max Act: 0.6236. Min Act: -0.0000

Data Index: 25785 (The Pile)

Max Activating Token Index: 536

Text #13

Max Range: 0.8255. Min Range: -0.8255

Max Act: 0.6143. Min Act: -0.0000

Data Index: 970394 (The Pile)

Max Activating Token Index: 332

Text #14

Max Range: 0.8255. Min Range: -0.8255

Max Act: 0.5732. Min Act: -0.0000

Data Index: 55973 (The Pile)

Max Activating Token Index: 945

Text #15

Max Range: 0.8255. Min Range: -0.8255

Max Act: 0.5986. Min Act: -0.0000

Data Index: 5942 (The Pile)

Max Activating Token Index: 518

Text #16

Max Range: 0.8255. Min Range: -0.8255

Max Act: 0.5989. Min Act: -0.0000

Data Index: 1411616 (The Pile)

Max Activating Token Index: 720

Text #17

Max Range: 0.8255. Min Range: -0.8255

Max Act: 0.5835. Min Act: -0.0000

Data Index: 1169468 (The Pile)

Max Activating Token Index: 253

Text #18

Max Range: 0.8255. Min Range: -0.8255

Max Act: 0.5956. Min Act: -0.0000

Data Index: 305259 (The Pile)

Max Activating Token Index: 792

Text #19

Max Range: 0.8255. Min Range: -0.8255

Max Act: 0.5752. Min Act: -0.0000

Data Index: 638119 (The Pile)

Max Activating Token Index: 139