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

Dataset: The Pile

Neuron 3354 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: 0.6703. Min Range: -0.6703

Max Act: 0.6703. Min Act: -0.0000

Data Index: 777537 (The Pile)

Max Activating Token Index: 366

Text #1

Max Range: 0.6703. Min Range: -0.6703

Max Act: 0.6321. Min Act: -0.0000

Data Index: 1767725 (The Pile)

Max Activating Token Index: 63

Text #2

Max Range: 0.6703. Min Range: -0.6703

Max Act: 0.6507. Min Act: -0.0000

Data Index: 289788 (The Pile)

Max Activating Token Index: 159

Text #3

Max Range: 0.6703. Min Range: -0.6703

Max Act: 0.6149. Min Act: -0.0000

Data Index: 1303969 (The Pile)

Max Activating Token Index: 901

Text #4

Max Range: 0.6703. Min Range: -0.6703

Max Act: 0.5876. Min Act: -0.0000

Data Index: 464280 (The Pile)

Max Activating Token Index: 717

Text #5

Max Range: 0.6703. Min Range: -0.6703

Max Act: 0.5408. Min Act: -0.0000

Data Index: 1746598 (The Pile)

Max Activating Token Index: 928

Text #6

Max Range: 0.6703. Min Range: -0.6703

Max Act: 0.5240. Min Act: -0.0000

Data Index: 483485 (The Pile)

Max Activating Token Index: 163

Text #7

Max Range: 0.6703. Min Range: -0.6703

Max Act: 0.5094. Min Act: -0.0000

Data Index: 49015 (The Pile)

Max Activating Token Index: 645

Text #8

Max Range: 0.6703. Min Range: -0.6703

Max Act: 0.5249. Min Act: -0.0000

Data Index: 1456408 (The Pile)

Max Activating Token Index: 131

Text #9

Max Range: 0.6703. Min Range: -0.6703

Max Act: 0.5216. Min Act: -0.0000

Data Index: 697253 (The Pile)

Max Activating Token Index: 1008

Text #10

Max Range: 0.6703. Min Range: -0.6703

Max Act: 0.5169. Min Act: -0.0000

Data Index: 2007 (The Pile)

Max Activating Token Index: 137

Text #11

Max Range: 0.6703. Min Range: -0.6703

Max Act: 0.4530. Min Act: -0.0000

Data Index: 1554128 (The Pile)

Max Activating Token Index: 700

Text #12

Max Range: 0.6703. Min Range: -0.6703

Max Act: 0.4318. Min Act: -0.0000

Data Index: 1649657 (The Pile)

Max Activating Token Index: 764

Text #13

Max Range: 0.6703. Min Range: -0.6703

Max Act: 0.4433. Min Act: -0.0000

Data Index: 740720 (The Pile)

Max Activating Token Index: 154

Text #14

Max Range: 0.6703. Min Range: -0.6703

Max Act: 0.4669. Min Act: -0.0000

Data Index: 1404976 (The Pile)

Max Activating Token Index: 418

Text #15

Max Range: 0.6703. Min Range: -0.6703

Max Act: 0.4660. Min Act: -0.0000

Data Index: 1365013 (The Pile)

Max Activating Token Index: 883

Text #16

Max Range: 0.6703. Min Range: -0.6703

Max Act: 0.4480. Min Act: -0.0000

Data Index: 126886 (The Pile)

Max Activating Token Index: 611

Text #17

Max Range: 0.6703. Min Range: -0.6703

Max Act: 0.4784. Min Act: -0.0000

Data Index: 1544901 (The Pile)

Max Activating Token Index: 362

Text #18

Max Range: 0.6703. Min Range: -0.6703

Max Act: 0.4712. Min Act: -0.0000

Data Index: 1524366 (The Pile)

Max Activating Token Index: 278

Text #19

Max Range: 0.6703. Min Range: -0.6703

Max Act: 0.4570. Min Act: -0.0000

Data Index: 1522347 (The Pile)

Max Activating Token Index: 457