Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1387 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 2.1024. Min Range: -2.1024

Max Act: 2.1024. Min Act: -0.0000

Data Index: 1112411 (The Pile)

Max Activating Token Index: 816

Text #1

Max Range: 2.1024. Min Range: -2.1024

Max Act: 1.4062. Min Act: -0.0000

Data Index: 1280710 (The Pile)

Max Activating Token Index: 129

Text #2

Max Range: 2.1024. Min Range: -2.1024

Max Act: 1.7879. Min Act: -0.0000

Data Index: 1721990 (The Pile)

Max Activating Token Index: 108

Text #3

Max Range: 2.1024. Min Range: -2.1024

Max Act: 1.6987. Min Act: -0.0000

Data Index: 1286370 (The Pile)

Max Activating Token Index: 266

Text #4

Max Range: 2.1024. Min Range: -2.1024

Max Act: 1.6037. Min Act: -0.0000

Data Index: 866465 (The Pile)

Max Activating Token Index: 143

Text #5

Max Range: 2.1024. Min Range: -2.1024

Max Act: 1.6178. Min Act: -0.0001

Data Index: 247509 (The Pile)

Max Activating Token Index: 168

Text #6

Max Range: 2.1024. Min Range: -2.1024

Max Act: 1.4669. Min Act: -0.0000

Data Index: 1595574 (The Pile)

Max Activating Token Index: 137

Text #7

Max Range: 2.1024. Min Range: -2.1024

Max Act: 1.6436. Min Act: -0.0001

Data Index: 462161 (The Pile)

Max Activating Token Index: 757

Text #8

Max Range: 2.1024. Min Range: -2.1024

Max Act: 1.2243. Min Act: -0.0000

Data Index: 1583843 (The Pile)

Max Activating Token Index: 66

Text #9

Max Range: 2.1024. Min Range: -2.1024

Max Act: 1.4090. Min Act: -0.0000

Data Index: 62095 (The Pile)

Max Activating Token Index: 614

Text #10

Max Range: 2.1024. Min Range: -2.1024

Max Act: 1.3031. Min Act: -0.0000

Data Index: 1010435 (The Pile)

Max Activating Token Index: 580

Text #11

Max Range: 2.1024. Min Range: -2.1024

Max Act: 1.3593. Min Act: -0.0000

Data Index: 1759751 (The Pile)

Max Activating Token Index: 223

Text #12

Max Range: 2.1024. Min Range: -2.1024

Max Act: 1.2507. Min Act: -0.0000

Data Index: 599872 (The Pile)

Max Activating Token Index: 226

Text #13

Max Range: 2.1024. Min Range: -2.1024

Max Act: 1.2382. Min Act: -0.0000

Data Index: 1484494 (The Pile)

Max Activating Token Index: 640

Text #14

Max Range: 2.1024. Min Range: -2.1024

Max Act: 1.3556. Min Act: -0.0000

Data Index: 1861309 (The Pile)

Max Activating Token Index: 287

Text #15

Max Range: 2.1024. Min Range: -2.1024

Max Act: 1.2288. Min Act: -0.0000

Data Index: 49245 (The Pile)

Max Activating Token Index: 48

Text #16

Max Range: 2.1024. Min Range: -2.1024

Max Act: 1.3607. Min Act: -0.0001

Data Index: 160390 (The Pile)

Max Activating Token Index: 84

Text #17

Max Range: 2.1024. Min Range: -2.1024

Max Act: 1.2562. Min Act: -0.0000

Data Index: 1381560 (The Pile)

Max Activating Token Index: 799

Text #18

Max Range: 2.1024. Min Range: -2.1024

Max Act: 1.2859. Min Act: -0.0000

Data Index: 1224962 (The Pile)

Max Activating Token Index: 20

Text #19

Max Range: 2.1024. Min Range: -2.1024

Max Act: 1.3187. Min Act: -0.0000

Data Index: 1808965 (The Pile)

Max Activating Token Index: 311