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

Dataset: The Pile

Neuron 1580 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2954. Min Range: -0.2954

Max Act: 0.2954. Min Act: -0.0000

Data Index: 431943 (The Pile)

Max Activating Token Index: 475

Text #1

Max Range: 0.2954. Min Range: -0.2954

Max Act: 0.2361. Min Act: -0.0000

Data Index: 1393640 (The Pile)

Max Activating Token Index: 106

Text #2

Max Range: 0.2954. Min Range: -0.2954

Max Act: 0.2456. Min Act: -0.0000

Data Index: 1256533 (The Pile)

Max Activating Token Index: 684

Text #3

Max Range: 0.2954. Min Range: -0.2954

Max Act: 0.2384. Min Act: -0.0000

Data Index: 1795791 (The Pile)

Max Activating Token Index: 283

Text #4

Max Range: 0.2954. Min Range: -0.2954

Max Act: 0.2477. Min Act: -0.0000

Data Index: 1086873 (The Pile)

Max Activating Token Index: 830

Text #5

Max Range: 0.2954. Min Range: -0.2954

Max Act: 0.2135. Min Act: -0.0000

Data Index: 1010220 (The Pile)

Max Activating Token Index: 765

Text #6

Max Range: 0.2954. Min Range: -0.2954

Max Act: 0.2035. Min Act: -0.0000

Data Index: 1253501 (The Pile)

Max Activating Token Index: 298

Text #7

Max Range: 0.2954. Min Range: -0.2954

Max Act: 0.2368. Min Act: -0.0000

Data Index: 481545 (The Pile)

Max Activating Token Index: 157

Text #8

Max Range: 0.2954. Min Range: -0.2954

Max Act: 0.2119. Min Act: -0.0000

Data Index: 158222 (The Pile)

Max Activating Token Index: 562

Text #9

Max Range: 0.2954. Min Range: -0.2954

Max Act: 0.2103. Min Act: -0.0000

Data Index: 1909910 (The Pile)

Max Activating Token Index: 185

Text #10

Max Range: 0.2954. Min Range: -0.2954

Max Act: 0.1704. Min Act: -0.0000

Data Index: 1553778 (The Pile)

Max Activating Token Index: 100

Text #11

Max Range: 0.2954. Min Range: -0.2954

Max Act: 0.1931. Min Act: -0.0000

Data Index: 1765733 (The Pile)

Max Activating Token Index: 96

Text #12

Max Range: 0.2954. Min Range: -0.2954

Max Act: 0.1817. Min Act: -0.0000

Data Index: 1421412 (The Pile)

Max Activating Token Index: 421

Text #13

Max Range: 0.2954. Min Range: -0.2954

Max Act: 0.1912. Min Act: -0.0000

Data Index: 1925976 (The Pile)

Max Activating Token Index: 693

Text #14

Max Range: 0.2954. Min Range: -0.2954

Max Act: 0.1698. Min Act: -0.0000

Data Index: 1601327 (The Pile)

Max Activating Token Index: 134

Text #15

Max Range: 0.2954. Min Range: -0.2954

Max Act: 0.2010. Min Act: -0.0000

Data Index: 1110957 (The Pile)

Max Activating Token Index: 687

Text #16

Max Range: 0.2954. Min Range: -0.2954

Max Act: 0.1689. Min Act: -0.0000

Data Index: 362603 (The Pile)

Max Activating Token Index: 714

Text #17

Max Range: 0.2954. Min Range: -0.2954

Max Act: 0.1702. Min Act: -0.0000

Data Index: 1128589 (The Pile)

Max Activating Token Index: 593

Text #18

Max Range: 0.2954. Min Range: -0.2954

Max Act: 0.2049. Min Act: -0.0000

Data Index: 1258323 (The Pile)

Max Activating Token Index: 693

Text #19

Max Range: 0.2954. Min Range: -0.2954

Max Act: 0.1869. Min Act: -0.0000

Data Index: 1161262 (The Pile)

Max Activating Token Index: 334