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

Dataset: The Pile

Neuron 69 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: 3.7688. Min Range: -3.7688

Max Act: 3.7688. Min Act: -0.0000

Data Index: 1245929 (The Pile)

Max Activating Token Index: 118

Text #1

Max Range: 3.7688. Min Range: -3.7688

Max Act: 3.2327. Min Act: -0.0000

Data Index: 989406 (The Pile)

Max Activating Token Index: 255

Text #2

Max Range: 3.7688. Min Range: -3.7688

Max Act: 3.4708. Min Act: -0.0000

Data Index: 1795795 (The Pile)

Max Activating Token Index: 869

Text #3

Max Range: 3.7688. Min Range: -3.7688

Max Act: 3.1031. Min Act: -0.0000

Data Index: 371220 (The Pile)

Max Activating Token Index: 951

Text #4

Max Range: 3.7688. Min Range: -3.7688

Max Act: 2.8730. Min Act: -0.0000

Data Index: 1695594 (The Pile)

Max Activating Token Index: 236

Text #5

Max Range: 3.7688. Min Range: -3.7688

Max Act: 2.2736. Min Act: -0.0000

Data Index: 502407 (The Pile)

Max Activating Token Index: 640

Text #6

Max Range: 3.7688. Min Range: -3.7688

Max Act: 2.5243. Min Act: -0.0000

Data Index: 1843580 (The Pile)

Max Activating Token Index: 882

Text #7

Max Range: 3.7688. Min Range: -3.7688

Max Act: 2.3889. Min Act: -0.0000

Data Index: 800648 (The Pile)

Max Activating Token Index: 509

Text #8

Max Range: 3.7688. Min Range: -3.7688

Max Act: 2.3255. Min Act: -0.0000

Data Index: 412007 (The Pile)

Max Activating Token Index: 28

Text #9

Max Range: 3.7688. Min Range: -3.7688

Max Act: 2.1393. Min Act: -0.0000

Data Index: 1125774 (The Pile)

Max Activating Token Index: 1006

Text #10

Max Range: 3.7688. Min Range: -3.7688

Max Act: 2.2018. Min Act: -0.0000

Data Index: 1470487 (The Pile)

Max Activating Token Index: 814

Text #11

Max Range: 3.7688. Min Range: -3.7688

Max Act: 2.3946. Min Act: -0.0000

Data Index: 1055430 (The Pile)

Max Activating Token Index: 122

Text #12

Max Range: 3.7688. Min Range: -3.7688

Max Act: 1.9448. Min Act: -0.0000

Data Index: 743950 (The Pile)

Max Activating Token Index: 69

Text #13

Max Range: 3.7688. Min Range: -3.7688

Max Act: 2.1250. Min Act: -0.0000

Data Index: 387617 (The Pile)

Max Activating Token Index: 520

Text #14

Max Range: 3.7688. Min Range: -3.7688

Max Act: 2.1082. Min Act: -0.0000

Data Index: 652649 (The Pile)

Max Activating Token Index: 828

Text #15

Max Range: 3.7688. Min Range: -3.7688

Max Act: 2.2095. Min Act: -0.0000

Data Index: 20666 (The Pile)

Max Activating Token Index: 16

Text #16

Max Range: 3.7688. Min Range: -3.7688

Max Act: 2.1870. Min Act: -0.0000

Data Index: 1177681 (The Pile)

Max Activating Token Index: 180

Text #17

Max Range: 3.7688. Min Range: -3.7688

Max Act: 2.1817. Min Act: -0.0000

Data Index: 1354794 (The Pile)

Max Activating Token Index: 157

Text #18

Max Range: 3.7688. Min Range: -3.7688

Max Act: 2.1244. Min Act: -0.0000

Data Index: 1268640 (The Pile)

Max Activating Token Index: 654

Text #19

Max Range: 3.7688. Min Range: -3.7688

Max Act: 1.9351. Min Act: -0.0000

Data Index: 1052451 (The Pile)

Max Activating Token Index: 839