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

Dataset: The Pile

Neuron 386 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: 1.2065. Min Range: -1.2065

Max Act: 1.2065. Min Act: -0.0000

Data Index: 1524828 (The Pile)

Max Activating Token Index: 466

Text #1

Max Range: 1.2065. Min Range: -1.2065

Max Act: 1.1965. Min Act: -0.0000

Data Index: 1126217 (The Pile)

Max Activating Token Index: 562

Text #2

Max Range: 1.2065. Min Range: -1.2065

Max Act: 0.8369. Min Act: -0.0000

Data Index: 1149906 (The Pile)

Max Activating Token Index: 37

Text #3

Max Range: 1.2065. Min Range: -1.2065

Max Act: 0.7759. Min Act: -0.0000

Data Index: 1582841 (The Pile)

Max Activating Token Index: 673

Text #4

Max Range: 1.2065. Min Range: -1.2065

Max Act: 0.6802. Min Act: -0.0000

Data Index: 734992 (The Pile)

Max Activating Token Index: 991

Text #5

Max Range: 1.2065. Min Range: -1.2065

Max Act: 0.7178. Min Act: -0.0000

Data Index: 701651 (The Pile)

Max Activating Token Index: 43

Text #6

Max Range: 1.2065. Min Range: -1.2065

Max Act: 0.7085. Min Act: -0.0000

Data Index: 639953 (The Pile)

Max Activating Token Index: 674

Text #7

Max Range: 1.2065. Min Range: -1.2065

Max Act: 0.6340. Min Act: -0.0000

Data Index: 43974 (The Pile)

Max Activating Token Index: 166

Text #8

Max Range: 1.2065. Min Range: -1.2065

Max Act: 0.6505. Min Act: -0.0000

Data Index: 1220798 (The Pile)

Max Activating Token Index: 224

Text #9

Max Range: 1.2065. Min Range: -1.2065

Max Act: 0.5848. Min Act: -0.0000

Data Index: 487667 (The Pile)

Max Activating Token Index: 285

Text #10

Max Range: 1.2065. Min Range: -1.2065

Max Act: 0.5696. Min Act: -0.0000

Data Index: 980513 (The Pile)

Max Activating Token Index: 524

Text #11

Max Range: 1.2065. Min Range: -1.2065

Max Act: 0.5470. Min Act: -0.0000

Data Index: 1832046 (The Pile)

Max Activating Token Index: 796

Text #12

Max Range: 1.2065. Min Range: -1.2065

Max Act: 0.6184. Min Act: -0.0000

Data Index: 372319 (The Pile)

Max Activating Token Index: 1002

Text #13

Max Range: 1.2065. Min Range: -1.2065

Max Act: 0.4864. Min Act: -0.0000

Data Index: 327193 (The Pile)

Max Activating Token Index: 116

Text #14

Max Range: 1.2065. Min Range: -1.2065

Max Act: 0.5207. Min Act: -0.0000

Data Index: 970743 (The Pile)

Max Activating Token Index: 986

Text #15

Max Range: 1.2065. Min Range: -1.2065

Max Act: 0.5189. Min Act: -0.0000

Data Index: 806388 (The Pile)

Max Activating Token Index: 399

Text #16

Max Range: 1.2065. Min Range: -1.2065

Max Act: 0.5530. Min Act: -0.0000

Data Index: 1932796 (The Pile)

Max Activating Token Index: 118

Text #17

Max Range: 1.2065. Min Range: -1.2065

Max Act: 0.5497. Min Act: -0.0000

Data Index: 1849250 (The Pile)

Max Activating Token Index: 18

Text #18

Max Range: 1.2065. Min Range: -1.2065

Max Act: 0.5635. Min Act: -0.0000

Data Index: 505359 (The Pile)

Max Activating Token Index: 793

Text #19

Max Range: 1.2065. Min Range: -1.2065

Max Act: 0.5361. Min Act: -0.0000

Data Index: 1769791 (The Pile)

Max Activating Token Index: 134