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

Dataset: The Pile

Neuron 4291 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 3.1904. Min Range: -3.1904

Max Act: 3.1904. Min Act: -0.0000

Data Index: 368290 (The Pile)

Max Activating Token Index: 162

Text #1

Max Range: 3.1904. Min Range: -3.1904

Max Act: 3.1231. Min Act: -0.0000

Data Index: 1606115 (The Pile)

Max Activating Token Index: 572

Text #2

Max Range: 3.1904. Min Range: -3.1904

Max Act: 2.8319. Min Act: -0.0000

Data Index: 62971 (The Pile)

Max Activating Token Index: 372

Text #3

Max Range: 3.1904. Min Range: -3.1904

Max Act: 2.6332. Min Act: -0.0000

Data Index: 1066987 (The Pile)

Max Activating Token Index: 402

Text #4

Max Range: 3.1904. Min Range: -3.1904

Max Act: 2.6015. Min Act: -0.0000

Data Index: 527372 (The Pile)

Max Activating Token Index: 113

Text #5

Max Range: 3.1904. Min Range: -3.1904

Max Act: 2.6931. Min Act: -0.0000

Data Index: 1472245 (The Pile)

Max Activating Token Index: 500

Text #6

Max Range: 3.1904. Min Range: -3.1904

Max Act: 2.5722. Min Act: -0.0000

Data Index: 303910 (The Pile)

Max Activating Token Index: 940

Text #7

Max Range: 3.1904. Min Range: -3.1904

Max Act: 2.7653. Min Act: -0.0000

Data Index: 122608 (The Pile)

Max Activating Token Index: 660

Text #8

Max Range: 3.1904. Min Range: -3.1904

Max Act: 2.5183. Min Act: -0.0000

Data Index: 456731 (The Pile)

Max Activating Token Index: 924

Text #9

Max Range: 3.1904. Min Range: -3.1904

Max Act: 2.5844. Min Act: -0.0000

Data Index: 43699 (The Pile)

Max Activating Token Index: 410

Text #10

Max Range: 3.1904. Min Range: -3.1904

Max Act: 2.8250. Min Act: -0.0000

Data Index: 1917867 (The Pile)

Max Activating Token Index: 698

Text #11

Max Range: 3.1904. Min Range: -3.1904

Max Act: 2.8130. Min Act: -0.0000

Data Index: 1013448 (The Pile)

Max Activating Token Index: 660

Text #12

Max Range: 3.1904. Min Range: -3.1904

Max Act: 2.5242. Min Act: -0.0000

Data Index: 1963524 (The Pile)

Max Activating Token Index: 581

Text #13

Max Range: 3.1904. Min Range: -3.1904

Max Act: 2.5051. Min Act: -0.0000

Data Index: 714403 (The Pile)

Max Activating Token Index: 188

Text #14

Max Range: 3.1904. Min Range: -3.1904

Max Act: 2.3657. Min Act: -0.0000

Data Index: 1019060 (The Pile)

Max Activating Token Index: 624

Text #15

Max Range: 3.1904. Min Range: -3.1904

Max Act: 2.7411. Min Act: -0.0000

Data Index: 1160841 (The Pile)

Max Activating Token Index: 935

Text #16

Max Range: 3.1904. Min Range: -3.1904

Max Act: 2.4761. Min Act: -0.0000

Data Index: 1645423 (The Pile)

Max Activating Token Index: 763

Text #17

Max Range: 3.1904. Min Range: -3.1904

Max Act: 2.4415. Min Act: -0.0000

Data Index: 570467 (The Pile)

Max Activating Token Index: 471

Text #18

Max Range: 3.1904. Min Range: -3.1904

Max Act: 2.5408. Min Act: -0.0000

Data Index: 1715519 (The Pile)

Max Activating Token Index: 615

Text #19

Max Range: 3.1904. Min Range: -3.1904

Max Act: 2.3948. Min Act: -0.0000

Data Index: 1022950 (The Pile)

Max Activating Token Index: 146