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

Dataset: The Pile

Neuron 1452 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: 3.1772. Min Range: -3.1772

Max Act: 3.1772. Min Act: -0.0000

Data Index: 1582564 (The Pile)

Max Activating Token Index: 429

Text #1

Max Range: 3.1772. Min Range: -3.1772

Max Act: 3.1631. Min Act: -0.0000

Data Index: 1132943 (The Pile)

Max Activating Token Index: 1010

Text #2

Max Range: 3.1772. Min Range: -3.1772

Max Act: 2.8286. Min Act: -0.0000

Data Index: 118708 (The Pile)

Max Activating Token Index: 239

Text #3

Max Range: 3.1772. Min Range: -3.1772

Max Act: 2.7536. Min Act: -0.0000

Data Index: 1795772 (The Pile)

Max Activating Token Index: 307

Text #4

Max Range: 3.1772. Min Range: -3.1772

Max Act: 2.5979. Min Act: -0.0000

Data Index: 1022106 (The Pile)

Max Activating Token Index: 647

Text #5

Max Range: 3.1772. Min Range: -3.1772

Max Act: 2.5945. Min Act: -0.0000

Data Index: 1413189 (The Pile)

Max Activating Token Index: 428

Text #6

Max Range: 3.1772. Min Range: -3.1772

Max Act: 2.5286. Min Act: -0.0000

Data Index: 276270 (The Pile)

Max Activating Token Index: 1009

Text #7

Max Range: 3.1772. Min Range: -3.1772

Max Act: 2.6328. Min Act: -0.0000

Data Index: 120105 (The Pile)

Max Activating Token Index: 516

Text #8

Max Range: 3.1772. Min Range: -3.1772

Max Act: 2.4978. Min Act: -0.0000

Data Index: 1637589 (The Pile)

Max Activating Token Index: 851

Text #9

Max Range: 3.1772. Min Range: -3.1772

Max Act: 2.5868. Min Act: -0.0000

Data Index: 633517 (The Pile)

Max Activating Token Index: 88

Text #10

Max Range: 3.1772. Min Range: -3.1772

Max Act: 2.4573. Min Act: -0.0000

Data Index: 1664286 (The Pile)

Max Activating Token Index: 231

Text #11

Max Range: 3.1772. Min Range: -3.1772

Max Act: 2.4038. Min Act: -0.0000

Data Index: 1128503 (The Pile)

Max Activating Token Index: 159

Text #12

Max Range: 3.1772. Min Range: -3.1772

Max Act: 2.1458. Min Act: -0.0000

Data Index: 1035645 (The Pile)

Max Activating Token Index: 906

Text #13

Max Range: 3.1772. Min Range: -3.1772

Max Act: 2.6456. Min Act: -0.0000

Data Index: 19110 (The Pile)

Max Activating Token Index: 711

Text #14

Max Range: 3.1772. Min Range: -3.1772

Max Act: 2.3657. Min Act: -0.0000

Data Index: 1283586 (The Pile)

Max Activating Token Index: 162

Text #15

Max Range: 3.1772. Min Range: -3.1772

Max Act: 2.2494. Min Act: -0.0000

Data Index: 128561 (The Pile)

Max Activating Token Index: 394

Text #16

Max Range: 3.1772. Min Range: -3.1772

Max Act: 2.2418. Min Act: -0.0000

Data Index: 1771377 (The Pile)

Max Activating Token Index: 702

Text #17

Max Range: 3.1772. Min Range: -3.1772

Max Act: 2.3484. Min Act: -0.0000

Data Index: 1261325 (The Pile)

Max Activating Token Index: 159

Text #18

Max Range: 3.1772. Min Range: -3.1772

Max Act: 1.9660. Min Act: -0.0000

Data Index: 1484411 (The Pile)

Max Activating Token Index: 831

Text #19

Max Range: 3.1772. Min Range: -3.1772

Max Act: 2.2072. Min Act: -0.0000

Data Index: 948556 (The Pile)

Max Activating Token Index: 308