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

Dataset: The Pile

Neuron 2602 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: 0.3087. Min Range: -0.3087

Max Act: 0.3087. Min Act: -0.0000

Data Index: 1791043 (The Pile)

Max Activating Token Index: 952

Text #1

Max Range: 0.3087. Min Range: -0.3087

Max Act: 0.2997. Min Act: -0.0000

Data Index: 313397 (The Pile)

Max Activating Token Index: 261

Text #2

Max Range: 0.3087. Min Range: -0.3087

Max Act: 0.2516. Min Act: -0.0000

Data Index: 1208315 (The Pile)

Max Activating Token Index: 256

Text #3

Max Range: 0.3087. Min Range: -0.3087

Max Act: 0.2375. Min Act: -0.0000

Data Index: 328584 (The Pile)

Max Activating Token Index: 925

Text #4

Max Range: 0.3087. Min Range: -0.3087

Max Act: 0.2419. Min Act: -0.0000

Data Index: 1429938 (The Pile)

Max Activating Token Index: 188

Text #5

Max Range: 0.3087. Min Range: -0.3087

Max Act: 0.2338. Min Act: -0.0000

Data Index: 404732 (The Pile)

Max Activating Token Index: 92

Text #6

Max Range: 0.3087. Min Range: -0.3087

Max Act: 0.2340. Min Act: -0.0000

Data Index: 1272696 (The Pile)

Max Activating Token Index: 491

Text #7

Max Range: 0.3087. Min Range: -0.3087

Max Act: 0.2337. Min Act: -0.0000

Data Index: 1643676 (The Pile)

Max Activating Token Index: 385

Text #8

Max Range: 0.3087. Min Range: -0.3087

Max Act: 0.2315. Min Act: -0.0000

Data Index: 636557 (The Pile)

Max Activating Token Index: 893

Text #9

Max Range: 0.3087. Min Range: -0.3087

Max Act: 0.2343. Min Act: -0.0000

Data Index: 1067357 (The Pile)

Max Activating Token Index: 63

Text #10

Max Range: 0.3087. Min Range: -0.3087

Max Act: 0.2290. Min Act: -0.0000

Data Index: 147228 (The Pile)

Max Activating Token Index: 46

Text #11

Max Range: 0.3087. Min Range: -0.3087

Max Act: 0.1822. Min Act: -0.0000

Data Index: 921356 (The Pile)

Max Activating Token Index: 267

Text #12

Max Range: 0.3087. Min Range: -0.3087

Max Act: 0.2229. Min Act: -0.0000

Data Index: 783845 (The Pile)

Max Activating Token Index: 179

Text #13

Max Range: 0.3087. Min Range: -0.3087

Max Act: 0.2224. Min Act: -0.0000

Data Index: 530285 (The Pile)

Max Activating Token Index: 914

Text #14

Max Range: 0.3087. Min Range: -0.3087

Max Act: 0.2016. Min Act: -0.0000

Data Index: 454331 (The Pile)

Max Activating Token Index: 499

Text #15

Max Range: 0.3087. Min Range: -0.3087

Max Act: 0.2065. Min Act: -0.0000

Data Index: 1533847 (The Pile)

Max Activating Token Index: 26

Text #16

Max Range: 0.3087. Min Range: -0.3087

Max Act: 0.2125. Min Act: -0.0000

Data Index: 555917 (The Pile)

Max Activating Token Index: 632

Text #17

Max Range: 0.3087. Min Range: -0.3087

Max Act: 0.2275. Min Act: -0.0000

Data Index: 427540 (The Pile)

Max Activating Token Index: 200

Text #18

Max Range: 0.3087. Min Range: -0.3087

Max Act: 0.1866. Min Act: -0.0000

Data Index: 1117894 (The Pile)

Max Activating Token Index: 1017

Text #19

Max Range: 0.3087. Min Range: -0.3087

Max Act: 0.2175. Min Act: -0.0000

Data Index: 635898 (The Pile)

Max Activating Token Index: 216