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

Dataset: The Pile

Neuron 4471 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: 4.4486. Min Range: -4.4486

Max Act: 4.3865. Min Act: -0.0000

Data Index: 904677 (The Pile)

Max Activating Token Index: 485

Text #1

Max Range: 4.4486. Min Range: -4.4486

Max Act: 4.4486. Min Act: -0.0000

Data Index: 1706845 (The Pile)

Max Activating Token Index: 610

Text #2

Max Range: 4.4486. Min Range: -4.4486

Max Act: 3.8395. Min Act: -0.0000

Data Index: 1545099 (The Pile)

Max Activating Token Index: 923

Text #3

Max Range: 4.4486. Min Range: -4.4486

Max Act: 4.1715. Min Act: -0.0000

Data Index: 321818 (The Pile)

Max Activating Token Index: 1013

Text #4

Max Range: 4.4486. Min Range: -4.4486

Max Act: 3.9356. Min Act: -0.0000

Data Index: 158841 (The Pile)

Max Activating Token Index: 858

Text #5

Max Range: 4.4486. Min Range: -4.4486

Max Act: 3.9159. Min Act: -0.0000

Data Index: 1686705 (The Pile)

Max Activating Token Index: 644

Text #6

Max Range: 4.4486. Min Range: -4.4486

Max Act: 3.7431. Min Act: -0.0000

Data Index: 804244 (The Pile)

Max Activating Token Index: 619

Text #7

Max Range: 4.4486. Min Range: -4.4486

Max Act: 4.2788. Min Act: -0.0000

Data Index: 1630282 (The Pile)

Max Activating Token Index: 295

Text #8

Max Range: 4.4486. Min Range: -4.4486

Max Act: 4.0716. Min Act: -0.0000

Data Index: 1377456 (The Pile)

Max Activating Token Index: 930

Text #9

Max Range: 4.4486. Min Range: -4.4486

Max Act: 4.2461. Min Act: -0.0000

Data Index: 699875 (The Pile)

Max Activating Token Index: 341

Text #10

Max Range: 4.4486. Min Range: -4.4486

Max Act: 3.8541. Min Act: -0.0000

Data Index: 189591 (The Pile)

Max Activating Token Index: 602

Text #11

Max Range: 4.4486. Min Range: -4.4486

Max Act: 4.1217. Min Act: -0.0000

Data Index: 460895 (The Pile)

Max Activating Token Index: 738

Text #12

Max Range: 4.4486. Min Range: -4.4486

Max Act: 4.0417. Min Act: -0.0000

Data Index: 856837 (The Pile)

Max Activating Token Index: 633

Text #13

Max Range: 4.4486. Min Range: -4.4486

Max Act: 3.8598. Min Act: -0.0000

Data Index: 776456 (The Pile)

Max Activating Token Index: 683

Text #14

Max Range: 4.4486. Min Range: -4.4486

Max Act: 3.8937. Min Act: -0.0000

Data Index: 974199 (The Pile)

Max Activating Token Index: 610

Text #15

Max Range: 4.4486. Min Range: -4.4486

Max Act: 4.1719. Min Act: -0.0000

Data Index: 1487409 (The Pile)

Max Activating Token Index: 501

Text #16

Max Range: 4.4486. Min Range: -4.4486

Max Act: 3.8587. Min Act: -0.0000

Data Index: 627130 (The Pile)

Max Activating Token Index: 534

Text #17

Max Range: 4.4486. Min Range: -4.4486

Max Act: 3.9536. Min Act: -0.0000

Data Index: 1426487 (The Pile)

Max Activating Token Index: 654

Text #18

Max Range: 4.4486. Min Range: -4.4486

Max Act: 4.1192. Min Act: -0.0000

Data Index: 1612124 (The Pile)

Max Activating Token Index: 259

Text #19

Max Range: 4.4486. Min Range: -4.4486

Max Act: 3.6309. Min Act: -0.0000

Data Index: 1964400 (The Pile)

Max Activating Token Index: 887