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

Dataset: The Pile

Neuron 593 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9179. Min Range: -0.9179

Max Act: 0.9179. Min Act: -0.0000

Data Index: 1129353 (The Pile)

Max Activating Token Index: 603

Text #1

Max Range: 0.9179. Min Range: -0.9179

Max Act: 0.8474. Min Act: -0.0000

Data Index: 323287 (The Pile)

Max Activating Token Index: 544

Text #2

Max Range: 0.9179. Min Range: -0.9179

Max Act: 0.7682. Min Act: -0.0000

Data Index: 67480 (The Pile)

Max Activating Token Index: 354

Text #3

Max Range: 0.9179. Min Range: -0.9179

Max Act: 0.7484. Min Act: -0.0000

Data Index: 484171 (The Pile)

Max Activating Token Index: 448

Text #4

Max Range: 0.9179. Min Range: -0.9179

Max Act: 0.7782. Min Act: -0.0000

Data Index: 1828922 (The Pile)

Max Activating Token Index: 488

Text #5

Max Range: 0.9179. Min Range: -0.9179

Max Act: 0.7260. Min Act: -0.0000

Data Index: 428592 (The Pile)

Max Activating Token Index: 360

Text #6

Max Range: 0.9179. Min Range: -0.9179

Max Act: 0.8356. Min Act: -0.0000

Data Index: 1334822 (The Pile)

Max Activating Token Index: 133

Text #7

Max Range: 0.9179. Min Range: -0.9179

Max Act: 0.6925. Min Act: -0.0000

Data Index: 1641690 (The Pile)

Max Activating Token Index: 203

Text #8

Max Range: 0.9179. Min Range: -0.9179

Max Act: 0.7020. Min Act: -0.0000

Data Index: 854801 (The Pile)

Max Activating Token Index: 458

Text #9

Max Range: 0.9179. Min Range: -0.9179

Max Act: 0.7209. Min Act: -0.0000

Data Index: 1742283 (The Pile)

Max Activating Token Index: 695

Text #10

Max Range: 0.9179. Min Range: -0.9179

Max Act: 0.6966. Min Act: -0.0000

Data Index: 1587368 (The Pile)

Max Activating Token Index: 597

Text #11

Max Range: 0.9179. Min Range: -0.9179

Max Act: 0.6956. Min Act: -0.0000

Data Index: 578600 (The Pile)

Max Activating Token Index: 683

Text #12

Max Range: 0.9179. Min Range: -0.9179

Max Act: 0.7328. Min Act: -0.0000

Data Index: 386903 (The Pile)

Max Activating Token Index: 989

Text #13

Max Range: 0.9179. Min Range: -0.9179

Max Act: 0.7238. Min Act: -0.0000

Data Index: 1070957 (The Pile)

Max Activating Token Index: 224

Text #14

Max Range: 0.9179. Min Range: -0.9179

Max Act: 0.6770. Min Act: -0.0000

Data Index: 1790055 (The Pile)

Max Activating Token Index: 635

Text #15

Max Range: 0.9179. Min Range: -0.9179

Max Act: 0.7151. Min Act: -0.0000

Data Index: 315537 (The Pile)

Max Activating Token Index: 363

Text #16

Max Range: 0.9179. Min Range: -0.9179

Max Act: 0.6482. Min Act: -0.0000

Data Index: 1805998 (The Pile)

Max Activating Token Index: 350

Text #17

Max Range: 0.9179. Min Range: -0.9179

Max Act: 0.7197. Min Act: -0.0000

Data Index: 1583039 (The Pile)

Max Activating Token Index: 749

Text #18

Max Range: 0.9179. Min Range: -0.9179

Max Act: 0.6630. Min Act: -0.0000

Data Index: 1860305 (The Pile)

Max Activating Token Index: 101

Text #19

Max Range: 0.9179. Min Range: -0.9179

Max Act: 0.6829. Min Act: -0.0000

Data Index: 1771869 (The Pile)

Max Activating Token Index: 622