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

Dataset: The Pile

Neuron 4087 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: 0.8155. Min Range: -0.8155

Max Act: 0.8155. Min Act: -0.0000

Data Index: 1475598 (The Pile)

Max Activating Token Index: 267

Text #1

Max Range: 0.8155. Min Range: -0.8155

Max Act: 0.7753. Min Act: -0.0000

Data Index: 1380460 (The Pile)

Max Activating Token Index: 381

Text #2

Max Range: 0.8155. Min Range: -0.8155

Max Act: 0.7200. Min Act: -0.0000

Data Index: 672387 (The Pile)

Max Activating Token Index: 389

Text #3

Max Range: 0.8155. Min Range: -0.8155

Max Act: 0.6851. Min Act: -0.0000

Data Index: 423868 (The Pile)

Max Activating Token Index: 34

Text #4

Max Range: 0.8155. Min Range: -0.8155

Max Act: 0.6973. Min Act: -0.0000

Data Index: 1589907 (The Pile)

Max Activating Token Index: 195

Text #5

Max Range: 0.8155. Min Range: -0.8155

Max Act: 0.6879. Min Act: -0.0000

Data Index: 1066488 (The Pile)

Max Activating Token Index: 387

Text #6

Max Range: 0.8155. Min Range: -0.8155

Max Act: 0.7029. Min Act: -0.0000

Data Index: 178303 (The Pile)

Max Activating Token Index: 552

Text #7

Max Range: 0.8155. Min Range: -0.8155

Max Act: 0.6389. Min Act: -0.0000

Data Index: 1489159 (The Pile)

Max Activating Token Index: 443

Text #8

Max Range: 0.8155. Min Range: -0.8155

Max Act: 0.6483. Min Act: -0.0000

Data Index: 1581105 (The Pile)

Max Activating Token Index: 103

Text #9

Max Range: 0.8155. Min Range: -0.8155

Max Act: 0.6252. Min Act: -0.0000

Data Index: 326185 (The Pile)

Max Activating Token Index: 478

Text #10

Max Range: 0.8155. Min Range: -0.8155

Max Act: 0.6435. Min Act: -0.0000

Data Index: 1621392 (The Pile)

Max Activating Token Index: 213

Text #11

Max Range: 0.8155. Min Range: -0.8155

Max Act: 0.6387. Min Act: -0.0000

Data Index: 1103286 (The Pile)

Max Activating Token Index: 89

Text #12

Max Range: 0.8155. Min Range: -0.8155

Max Act: 0.6209. Min Act: -0.0000

Data Index: 1098955 (The Pile)

Max Activating Token Index: 779

Text #13

Max Range: 0.8155. Min Range: -0.8155

Max Act: 0.6193. Min Act: -0.0000

Data Index: 349499 (The Pile)

Max Activating Token Index: 155

Text #14

Max Range: 0.8155. Min Range: -0.8155

Max Act: 0.6373. Min Act: -0.0000

Data Index: 1211656 (The Pile)

Max Activating Token Index: 910

Text #15

Max Range: 0.8155. Min Range: -0.8155

Max Act: 0.6138. Min Act: -0.0000

Data Index: 751495 (The Pile)

Max Activating Token Index: 244

Text #16

Max Range: 0.8155. Min Range: -0.8155

Max Act: 0.5716. Min Act: -0.0000

Data Index: 468903 (The Pile)

Max Activating Token Index: 98

Text #17

Max Range: 0.8155. Min Range: -0.8155

Max Act: 0.5955. Min Act: -0.0000

Data Index: 74915 (The Pile)

Max Activating Token Index: 863

Text #18

Max Range: 0.8155. Min Range: -0.8155

Max Act: 0.6576. Min Act: -0.0000

Data Index: 801618 (The Pile)

Max Activating Token Index: 484

Text #19

Max Range: 0.8155. Min Range: -0.8155

Max Act: 0.6272. Min Act: -0.0000

Data Index: 188249 (The Pile)

Max Activating Token Index: 504