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

Dataset: The Pile

Neuron 4154 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: 3.3635. Min Range: -3.3635

Max Act: 3.3530. Min Act: -0.0000

Data Index: 1123047 (The Pile)

Max Activating Token Index: 56

Text #1

Max Range: 3.3635. Min Range: -3.3635

Max Act: 3.3635. Min Act: -0.0000

Data Index: 1921944 (The Pile)

Max Activating Token Index: 53

Text #2

Max Range: 3.3635. Min Range: -3.3635

Max Act: 2.9713. Min Act: -0.0000

Data Index: 641201 (The Pile)

Max Activating Token Index: 606

Text #3

Max Range: 3.3635. Min Range: -3.3635

Max Act: 2.9631. Min Act: -0.0000

Data Index: 1005092 (The Pile)

Max Activating Token Index: 107

Text #4

Max Range: 3.3635. Min Range: -3.3635

Max Act: 3.2121. Min Act: -0.0000

Data Index: 493315 (The Pile)

Max Activating Token Index: 431

Text #5

Max Range: 3.3635. Min Range: -3.3635

Max Act: 3.0422. Min Act: -0.0000

Data Index: 790924 (The Pile)

Max Activating Token Index: 431

Text #6

Max Range: 3.3635. Min Range: -3.3635

Max Act: 2.8641. Min Act: -0.0000

Data Index: 642014 (The Pile)

Max Activating Token Index: 86

Text #7

Max Range: 3.3635. Min Range: -3.3635

Max Act: 3.0575. Min Act: -0.0000

Data Index: 1894865 (The Pile)

Max Activating Token Index: 32

Text #8

Max Range: 3.3635. Min Range: -3.3635

Max Act: 2.8899. Min Act: -0.0000

Data Index: 1457655 (The Pile)

Max Activating Token Index: 85

Text #9

Max Range: 3.3635. Min Range: -3.3635

Max Act: 3.0541. Min Act: -0.0000

Data Index: 688952 (The Pile)

Max Activating Token Index: 594

Text #10

Max Range: 3.3635. Min Range: -3.3635

Max Act: 2.8066. Min Act: -0.0000

Data Index: 663335 (The Pile)

Max Activating Token Index: 110

Text #11

Max Range: 3.3635. Min Range: -3.3635

Max Act: 2.6703. Min Act: -0.0000

Data Index: 1732856 (The Pile)

Max Activating Token Index: 205

Text #12

Max Range: 3.3635. Min Range: -3.3635

Max Act: 2.8064. Min Act: -0.0000

Data Index: 1008438 (The Pile)

Max Activating Token Index: 356

Text #13

Max Range: 3.3635. Min Range: -3.3635

Max Act: 2.7177. Min Act: -0.0000

Data Index: 1372895 (The Pile)

Max Activating Token Index: 32

Text #14

Max Range: 3.3635. Min Range: -3.3635

Max Act: 2.5163. Min Act: -0.0000

Data Index: 1670741 (The Pile)

Max Activating Token Index: 189

Text #15

Max Range: 3.3635. Min Range: -3.3635

Max Act: 2.7882. Min Act: -0.0000

Data Index: 482239 (The Pile)

Max Activating Token Index: 412

Text #16

Max Range: 3.3635. Min Range: -3.3635

Max Act: 2.6532. Min Act: -0.0000

Data Index: 778228 (The Pile)

Max Activating Token Index: 84

Text #17

Max Range: 3.3635. Min Range: -3.3635

Max Act: 2.6205. Min Act: -0.0000

Data Index: 869966 (The Pile)

Max Activating Token Index: 516

Text #18

Max Range: 3.3635. Min Range: -3.3635

Max Act: 2.7466. Min Act: -0.0000

Data Index: 219413 (The Pile)

Max Activating Token Index: 509

Text #19

Max Range: 3.3635. Min Range: -3.3635

Max Act: 2.4674. Min Act: -0.0000

Data Index: 1485727 (The Pile)

Max Activating Token Index: 51