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

Dataset: The Pile

Neuron 4470 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5216. Min Range: -1.5216

Max Act: 1.4782. Min Act: -0.0000

Data Index: 1582262 (The Pile)

Max Activating Token Index: 654

Text #1

Max Range: 1.5216. Min Range: -1.5216

Max Act: 1.3404. Min Act: -0.0000

Data Index: 1011144 (The Pile)

Max Activating Token Index: 442

Text #2

Max Range: 1.5216. Min Range: -1.5216

Max Act: 1.5216. Min Act: -0.0000

Data Index: 976251 (The Pile)

Max Activating Token Index: 679

Text #3

Max Range: 1.5216. Min Range: -1.5216

Max Act: 1.2316. Min Act: -0.0000

Data Index: 572690 (The Pile)

Max Activating Token Index: 661

Text #4

Max Range: 1.5216. Min Range: -1.5216

Max Act: 1.2441. Min Act: -0.0000

Data Index: 771191 (The Pile)

Max Activating Token Index: 436

Text #5

Max Range: 1.5216. Min Range: -1.5216

Max Act: 1.2816. Min Act: -0.0000

Data Index: 1212195 (The Pile)

Max Activating Token Index: 402

Text #6

Max Range: 1.5216. Min Range: -1.5216

Max Act: 1.4157. Min Act: -0.0000

Data Index: 1522199 (The Pile)

Max Activating Token Index: 599

Text #7

Max Range: 1.5216. Min Range: -1.5216

Max Act: 1.1868. Min Act: -0.0000

Data Index: 1529333 (The Pile)

Max Activating Token Index: 126

Text #8

Max Range: 1.5216. Min Range: -1.5216

Max Act: 1.2795. Min Act: -0.0000

Data Index: 1135983 (The Pile)

Max Activating Token Index: 434

Text #9

Max Range: 1.5216. Min Range: -1.5216

Max Act: 1.2512. Min Act: -0.0000

Data Index: 639872 (The Pile)

Max Activating Token Index: 830

Text #10

Max Range: 1.5216. Min Range: -1.5216

Max Act: 1.2674. Min Act: -0.0000

Data Index: 1731116 (The Pile)

Max Activating Token Index: 321

Text #11

Max Range: 1.5216. Min Range: -1.5216

Max Act: 1.2157. Min Act: -0.0000

Data Index: 1365099 (The Pile)

Max Activating Token Index: 761

Text #12

Max Range: 1.5216. Min Range: -1.5216

Max Act: 1.1126. Min Act: -0.0000

Data Index: 1198237 (The Pile)

Max Activating Token Index: 210

Text #13

Max Range: 1.5216. Min Range: -1.5216

Max Act: 1.2765. Min Act: -0.0000

Data Index: 162747 (The Pile)

Max Activating Token Index: 605

Text #14

Max Range: 1.5216. Min Range: -1.5216

Max Act: 1.2435. Min Act: -0.0000

Data Index: 1773241 (The Pile)

Max Activating Token Index: 870

Text #15

Max Range: 1.5216. Min Range: -1.5216

Max Act: 1.1107. Min Act: -0.0000

Data Index: 457893 (The Pile)

Max Activating Token Index: 114

Text #16

Max Range: 1.5216. Min Range: -1.5216

Max Act: 1.2243. Min Act: -0.0000

Data Index: 35527 (The Pile)

Max Activating Token Index: 150

Text #17

Max Range: 1.5216. Min Range: -1.5216

Max Act: 1.1467. Min Act: -0.0000

Data Index: 67051 (The Pile)

Max Activating Token Index: 424

Text #18

Max Range: 1.5216. Min Range: -1.5216

Max Act: 1.1373. Min Act: -0.0000

Data Index: 1083758 (The Pile)

Max Activating Token Index: 937

Text #19

Max Range: 1.5216. Min Range: -1.5216

Max Act: 1.0527. Min Act: -0.0000

Data Index: 1475381 (The Pile)

Max Activating Token Index: 498