Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2278 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.9600. Min Range: -0.9600

Max Act: 0.9600. Min Act: -0.0000

Data Index: 1684800 (The Pile)

Max Activating Token Index: 71

Text #1

Max Range: 0.9600. Min Range: -0.9600

Max Act: 0.8967. Min Act: -0.0000

Data Index: 1451381 (The Pile)

Max Activating Token Index: 200

Text #2

Max Range: 0.9600. Min Range: -0.9600

Max Act: 0.8734. Min Act: -0.0000

Data Index: 407049 (The Pile)

Max Activating Token Index: 594

Text #3

Max Range: 0.9600. Min Range: -0.9600

Max Act: 0.7467. Min Act: -0.0000

Data Index: 222658 (The Pile)

Max Activating Token Index: 225

Text #4

Max Range: 0.9600. Min Range: -0.9600

Max Act: 0.8043. Min Act: -0.0000

Data Index: 324492 (The Pile)

Max Activating Token Index: 120

Text #5

Max Range: 0.9600. Min Range: -0.9600

Max Act: 0.7566. Min Act: -0.0000

Data Index: 549718 (The Pile)

Max Activating Token Index: 33

Text #6

Max Range: 0.9600. Min Range: -0.9600

Max Act: 0.7394. Min Act: -0.0000

Data Index: 1055645 (The Pile)

Max Activating Token Index: 81

Text #7

Max Range: 0.9600. Min Range: -0.9600

Max Act: 0.7731. Min Act: -0.0000

Data Index: 1133922 (The Pile)

Max Activating Token Index: 516

Text #8

Max Range: 0.9600. Min Range: -0.9600

Max Act: 0.7491. Min Act: -0.0000

Data Index: 1627489 (The Pile)

Max Activating Token Index: 213

Text #9

Max Range: 0.9600. Min Range: -0.9600

Max Act: 0.7377. Min Act: -0.0000

Data Index: 39659 (The Pile)

Max Activating Token Index: 420

Text #10

Max Range: 0.9600. Min Range: -0.9600

Max Act: 0.7465. Min Act: -0.0000

Data Index: 670718 (The Pile)

Max Activating Token Index: 312

Text #11

Max Range: 0.9600. Min Range: -0.9600

Max Act: 0.7263. Min Act: -0.0000

Data Index: 1648921 (The Pile)

Max Activating Token Index: 693

Text #12

Max Range: 0.9600. Min Range: -0.9600

Max Act: 0.6976. Min Act: -0.0000

Data Index: 1718651 (The Pile)

Max Activating Token Index: 546

Text #13

Max Range: 0.9600. Min Range: -0.9600

Max Act: 0.6542. Min Act: -0.0000

Data Index: 509170 (The Pile)

Max Activating Token Index: 231

Text #14

Max Range: 0.9600. Min Range: -0.9600

Max Act: 0.6586. Min Act: -0.0000

Data Index: 1322740 (The Pile)

Max Activating Token Index: 146

Text #15

Max Range: 0.9600. Min Range: -0.9600

Max Act: 0.7109. Min Act: -0.0000

Data Index: 1761884 (The Pile)

Max Activating Token Index: 679

Text #16

Max Range: 0.9600. Min Range: -0.9600

Max Act: 0.6375. Min Act: -0.0000

Data Index: 83023 (The Pile)

Max Activating Token Index: 999

Text #17

Max Range: 0.9600. Min Range: -0.9600

Max Act: 0.6554. Min Act: -0.0000

Data Index: 1409604 (The Pile)

Max Activating Token Index: 887

Text #18

Max Range: 0.9600. Min Range: -0.9600

Max Act: 0.6507. Min Act: -0.0000

Data Index: 1613767 (The Pile)

Max Activating Token Index: 341

Text #19

Max Range: 0.9600. Min Range: -0.9600

Max Act: 0.6204. Min Act: -0.0000

Data Index: 1110274 (The Pile)

Max Activating Token Index: 59