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

Dataset: The Pile

Neuron 3659 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: 1.3717. Min Range: -1.3717

Max Act: 1.3717. Min Act: -0.0000

Data Index: 1149427 (The Pile)

Max Activating Token Index: 115

Text #1

Max Range: 1.3717. Min Range: -1.3717

Max Act: 1.3586. Min Act: -0.0000

Data Index: 1969109 (The Pile)

Max Activating Token Index: 728

Text #2

Max Range: 1.3717. Min Range: -1.3717

Max Act: 1.3310. Min Act: -0.0000

Data Index: 1527665 (The Pile)

Max Activating Token Index: 763

Text #3

Max Range: 1.3717. Min Range: -1.3717

Max Act: 1.2674. Min Act: -0.0000

Data Index: 1990623 (The Pile)

Max Activating Token Index: 648

Text #4

Max Range: 1.3717. Min Range: -1.3717

Max Act: 1.0974. Min Act: -0.0000

Data Index: 895619 (The Pile)

Max Activating Token Index: 991

Text #5

Max Range: 1.3717. Min Range: -1.3717

Max Act: 1.1649. Min Act: -0.0000

Data Index: 90027 (The Pile)

Max Activating Token Index: 744

Text #6

Max Range: 1.3717. Min Range: -1.3717

Max Act: 1.0535. Min Act: -0.0000

Data Index: 161534 (The Pile)

Max Activating Token Index: 296

Text #7

Max Range: 1.3717. Min Range: -1.3717

Max Act: 1.0412. Min Act: -0.0000

Data Index: 154470 (The Pile)

Max Activating Token Index: 116

Text #8

Max Range: 1.3717. Min Range: -1.3717

Max Act: 1.0683. Min Act: -0.0000

Data Index: 1659126 (The Pile)

Max Activating Token Index: 268

Text #9

Max Range: 1.3717. Min Range: -1.3717

Max Act: 1.0416. Min Act: -0.0000

Data Index: 433866 (The Pile)

Max Activating Token Index: 123

Text #10

Max Range: 1.3717. Min Range: -1.3717

Max Act: 0.9469. Min Act: -0.0000

Data Index: 501693 (The Pile)

Max Activating Token Index: 128

Text #11

Max Range: 1.3717. Min Range: -1.3717

Max Act: 0.9764. Min Act: -0.0000

Data Index: 1401283 (The Pile)

Max Activating Token Index: 241

Text #12

Max Range: 1.3717. Min Range: -1.3717

Max Act: 0.9859. Min Act: -0.0000

Data Index: 271209 (The Pile)

Max Activating Token Index: 486

Text #13

Max Range: 1.3717. Min Range: -1.3717

Max Act: 0.8729. Min Act: -0.0000

Data Index: 1550737 (The Pile)

Max Activating Token Index: 860

Text #14

Max Range: 1.3717. Min Range: -1.3717

Max Act: 0.9630. Min Act: -0.0000

Data Index: 892256 (The Pile)

Max Activating Token Index: 719

Text #15

Max Range: 1.3717. Min Range: -1.3717

Max Act: 0.9491. Min Act: -0.0000

Data Index: 1827198 (The Pile)

Max Activating Token Index: 27

Text #16

Max Range: 1.3717. Min Range: -1.3717

Max Act: 0.9213. Min Act: -0.0000

Data Index: 70270 (The Pile)

Max Activating Token Index: 142

Text #17

Max Range: 1.3717. Min Range: -1.3717

Max Act: 0.8652. Min Act: -0.0000

Data Index: 892465 (The Pile)

Max Activating Token Index: 60

Text #18

Max Range: 1.3717. Min Range: -1.3717

Max Act: 0.9423. Min Act: -0.0000

Data Index: 1530083 (The Pile)

Max Activating Token Index: 747

Text #19

Max Range: 1.3717. Min Range: -1.3717

Max Act: 0.9221. Min Act: -0.0000

Data Index: 1339005 (The Pile)

Max Activating Token Index: 692