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

Dataset: The Pile

Neuron 1075 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: 1.7975. Min Range: -1.7975

Max Act: 1.7975. Min Act: -0.0000

Data Index: 1595061 (The Pile)

Max Activating Token Index: 407

Text #1

Max Range: 1.7975. Min Range: -1.7975

Max Act: 1.6662. Min Act: -0.0000

Data Index: 1567126 (The Pile)

Max Activating Token Index: 340

Text #2

Max Range: 1.7975. Min Range: -1.7975

Max Act: 1.5094. Min Act: -0.0000

Data Index: 1669280 (The Pile)

Max Activating Token Index: 89

Text #3

Max Range: 1.7975. Min Range: -1.7975

Max Act: 1.5007. Min Act: -0.0000

Data Index: 1777534 (The Pile)

Max Activating Token Index: 803

Text #4

Max Range: 1.7975. Min Range: -1.7975

Max Act: 1.5094. Min Act: -0.0000

Data Index: 164065 (The Pile)

Max Activating Token Index: 748

Text #5

Max Range: 1.7975. Min Range: -1.7975

Max Act: 1.4129. Min Act: -0.0000

Data Index: 1815030 (The Pile)

Max Activating Token Index: 932

Text #6

Max Range: 1.7975. Min Range: -1.7975

Max Act: 1.3674. Min Act: -0.0000

Data Index: 276334 (The Pile)

Max Activating Token Index: 11

Text #7

Max Range: 1.7975. Min Range: -1.7975

Max Act: 1.5215. Min Act: -0.0000

Data Index: 122646 (The Pile)

Max Activating Token Index: 402

Text #8

Max Range: 1.7975. Min Range: -1.7975

Max Act: 1.3062. Min Act: -0.0000

Data Index: 1267584 (The Pile)

Max Activating Token Index: 460

Text #9

Max Range: 1.7975. Min Range: -1.7975

Max Act: 1.3362. Min Act: -0.0000

Data Index: 1295247 (The Pile)

Max Activating Token Index: 34

Text #10

Max Range: 1.7975. Min Range: -1.7975

Max Act: 1.2558. Min Act: -0.0000

Data Index: 1029189 (The Pile)

Max Activating Token Index: 11

Text #11

Max Range: 1.7975. Min Range: -1.7975

Max Act: 1.2983. Min Act: -0.0000

Data Index: 536200 (The Pile)

Max Activating Token Index: 11

Text #12

Max Range: 1.7975. Min Range: -1.7975

Max Act: 1.2530. Min Act: -0.0000

Data Index: 1640678 (The Pile)

Max Activating Token Index: 867

Text #13

Max Range: 1.7975. Min Range: -1.7975

Max Act: 1.2797. Min Act: -0.0000

Data Index: 1921551 (The Pile)

Max Activating Token Index: 439

Text #14

Max Range: 1.7975. Min Range: -1.7975

Max Act: 1.1945. Min Act: -0.0000

Data Index: 1987975 (The Pile)

Max Activating Token Index: 752

Text #15

Max Range: 1.7975. Min Range: -1.7975

Max Act: 1.3480. Min Act: -0.0000

Data Index: 972908 (The Pile)

Max Activating Token Index: 628

Text #16

Max Range: 1.7975. Min Range: -1.7975

Max Act: 1.3233. Min Act: -0.0000

Data Index: 1289891 (The Pile)

Max Activating Token Index: 861

Text #17

Max Range: 1.7975. Min Range: -1.7975

Max Act: 1.3176. Min Act: -0.0000

Data Index: 1536366 (The Pile)

Max Activating Token Index: 700

Text #18

Max Range: 1.7975. Min Range: -1.7975

Max Act: 1.2055. Min Act: -0.0000

Data Index: 1324178 (The Pile)

Max Activating Token Index: 472

Text #19

Max Range: 1.7975. Min Range: -1.7975

Max Act: 1.1604. Min Act: -0.0000

Data Index: 1748565 (The Pile)

Max Activating Token Index: 295