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

Dataset: The Pile

Neuron 393 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6612. Min Range: -1.6612

Max Act: 1.6612. Min Act: -0.0000

Data Index: 390408 (The Pile)

Max Activating Token Index: 1008

Text #1

Max Range: 1.6612. Min Range: -1.6612

Max Act: 1.4809. Min Act: -0.0000

Data Index: 690651 (The Pile)

Max Activating Token Index: 586

Text #2

Max Range: 1.6612. Min Range: -1.6612

Max Act: 1.4343. Min Act: -0.0000

Data Index: 784538 (The Pile)

Max Activating Token Index: 751

Text #3

Max Range: 1.6612. Min Range: -1.6612

Max Act: 1.3494. Min Act: -0.0000

Data Index: 422486 (The Pile)

Max Activating Token Index: 1022

Text #4

Max Range: 1.6612. Min Range: -1.6612

Max Act: 1.3881. Min Act: -0.0000

Data Index: 1170097 (The Pile)

Max Activating Token Index: 106

Text #5

Max Range: 1.6612. Min Range: -1.6612

Max Act: 1.3675. Min Act: -0.0000

Data Index: 283104 (The Pile)

Max Activating Token Index: 227

Text #6

Max Range: 1.6612. Min Range: -1.6612

Max Act: 1.2733. Min Act: -0.0000

Data Index: 1611812 (The Pile)

Max Activating Token Index: 599

Text #7

Max Range: 1.6612. Min Range: -1.6612

Max Act: 1.3350. Min Act: -0.0000

Data Index: 543803 (The Pile)

Max Activating Token Index: 543

Text #8

Max Range: 1.6612. Min Range: -1.6612

Max Act: 1.3329. Min Act: -0.0000

Data Index: 602454 (The Pile)

Max Activating Token Index: 762

Text #9

Max Range: 1.6612. Min Range: -1.6612

Max Act: 1.4017. Min Act: -0.0000

Data Index: 72649 (The Pile)

Max Activating Token Index: 331

Text #10

Max Range: 1.6612. Min Range: -1.6612

Max Act: 1.3621. Min Act: -0.0000

Data Index: 31313 (The Pile)

Max Activating Token Index: 785

Text #11

Max Range: 1.6612. Min Range: -1.6612

Max Act: 1.3317. Min Act: -0.0000

Data Index: 230045 (The Pile)

Max Activating Token Index: 720

Text #12

Max Range: 1.6612. Min Range: -1.6612

Max Act: 1.2725. Min Act: -0.0000

Data Index: 1329867 (The Pile)

Max Activating Token Index: 400

Text #13

Max Range: 1.6612. Min Range: -1.6612

Max Act: 1.2741. Min Act: -0.0000

Data Index: 273072 (The Pile)

Max Activating Token Index: 350

Text #14

Max Range: 1.6612. Min Range: -1.6612

Max Act: 1.1964. Min Act: -0.0000

Data Index: 562781 (The Pile)

Max Activating Token Index: 57

Text #15

Max Range: 1.6612. Min Range: -1.6612

Max Act: 1.3365. Min Act: -0.0000

Data Index: 415956 (The Pile)

Max Activating Token Index: 586

Text #16

Max Range: 1.6612. Min Range: -1.6612

Max Act: 1.3122. Min Act: -0.0000

Data Index: 1452400 (The Pile)

Max Activating Token Index: 557

Text #17

Max Range: 1.6612. Min Range: -1.6612

Max Act: 1.0465. Min Act: -0.0000

Data Index: 1217265 (The Pile)

Max Activating Token Index: 827

Text #18

Max Range: 1.6612. Min Range: -1.6612

Max Act: 1.3076. Min Act: -0.0000

Data Index: 1763010 (The Pile)

Max Activating Token Index: 51

Text #19

Max Range: 1.6612. Min Range: -1.6612

Max Act: 1.1681. Min Act: -0.0000

Data Index: 1777857 (The Pile)

Max Activating Token Index: 822