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

Dataset: The Pile

Neuron 1621 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: 5.9223. Min Range: -5.9223

Max Act: 5.9223. Min Act: -0.0000

Data Index: 1831921 (The Pile)

Max Activating Token Index: 509

Text #1

Max Range: 5.9223. Min Range: -5.9223

Max Act: 5.4375. Min Act: -0.0000

Data Index: 831590 (The Pile)

Max Activating Token Index: 576

Text #2

Max Range: 5.9223. Min Range: -5.9223

Max Act: 5.6801. Min Act: -0.0000

Data Index: 1503119 (The Pile)

Max Activating Token Index: 1001

Text #3

Max Range: 5.9223. Min Range: -5.9223

Max Act: 5.3000. Min Act: -0.0000

Data Index: 981206 (The Pile)

Max Activating Token Index: 19

Text #4

Max Range: 5.9223. Min Range: -5.9223

Max Act: 5.1785. Min Act: -0.0000

Data Index: 1623836 (The Pile)

Max Activating Token Index: 974

Text #5

Max Range: 5.9223. Min Range: -5.9223

Max Act: 5.4722. Min Act: -0.0000

Data Index: 893166 (The Pile)

Max Activating Token Index: 589

Text #6

Max Range: 5.9223. Min Range: -5.9223

Max Act: 5.6297. Min Act: -0.0000

Data Index: 384738 (The Pile)

Max Activating Token Index: 846

Text #7

Max Range: 5.9223. Min Range: -5.9223

Max Act: 5.3640. Min Act: -0.0000

Data Index: 510904 (The Pile)

Max Activating Token Index: 380

Text #8

Max Range: 5.9223. Min Range: -5.9223

Max Act: 5.3680. Min Act: -0.0000

Data Index: 942219 (The Pile)

Max Activating Token Index: 101

Text #9

Max Range: 5.9223. Min Range: -5.9223

Max Act: 5.3464. Min Act: -0.0000

Data Index: 1255302 (The Pile)

Max Activating Token Index: 700

Text #10

Max Range: 5.9223. Min Range: -5.9223

Max Act: 5.1487. Min Act: -0.0000

Data Index: 858997 (The Pile)

Max Activating Token Index: 246

Text #11

Max Range: 5.9223. Min Range: -5.9223

Max Act: 5.5349. Min Act: -0.0000

Data Index: 960738 (The Pile)

Max Activating Token Index: 775

Text #12

Max Range: 5.9223. Min Range: -5.9223

Max Act: 4.7858. Min Act: -0.0000

Data Index: 1073272 (The Pile)

Max Activating Token Index: 1008

Text #13

Max Range: 5.9223. Min Range: -5.9223

Max Act: 5.2276. Min Act: -0.0000

Data Index: 1846624 (The Pile)

Max Activating Token Index: 994

Text #14

Max Range: 5.9223. Min Range: -5.9223

Max Act: 5.2415. Min Act: -0.0000

Data Index: 1262257 (The Pile)

Max Activating Token Index: 477

Text #15

Max Range: 5.9223. Min Range: -5.9223

Max Act: 5.2311. Min Act: -0.0000

Data Index: 878526 (The Pile)

Max Activating Token Index: 772

Text #16

Max Range: 5.9223. Min Range: -5.9223

Max Act: 5.0623. Min Act: -0.0000

Data Index: 1432480 (The Pile)

Max Activating Token Index: 422

Text #17

Max Range: 5.9223. Min Range: -5.9223

Max Act: 5.2060. Min Act: -0.0000

Data Index: 1624301 (The Pile)

Max Activating Token Index: 147

Text #18

Max Range: 5.9223. Min Range: -5.9223

Max Act: 5.2320. Min Act: -0.0000

Data Index: 99406 (The Pile)

Max Activating Token Index: 170

Text #19

Max Range: 5.9223. Min Range: -5.9223

Max Act: 5.2375. Min Act: -0.0000

Data Index: 1212008 (The Pile)

Max Activating Token Index: 376