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

Dataset: The Pile

Neuron 3217 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2931. Min Range: -0.2931

Max Act: 0.2931. Min Act: -0.0000

Data Index: 1613513 (The Pile)

Max Activating Token Index: 528

Text #1

Max Range: 0.2931. Min Range: -0.2931

Max Act: 0.2813. Min Act: -0.0000

Data Index: 473694 (The Pile)

Max Activating Token Index: 147

Text #2

Max Range: 0.2931. Min Range: -0.2931

Max Act: 0.2829. Min Act: -0.0000

Data Index: 177491 (The Pile)

Max Activating Token Index: 428

Text #3

Max Range: 0.2931. Min Range: -0.2931

Max Act: 0.2368. Min Act: -0.0000

Data Index: 1473306 (The Pile)

Max Activating Token Index: 38

Text #4

Max Range: 0.2931. Min Range: -0.2931

Max Act: 0.2482. Min Act: -0.0000

Data Index: 1299702 (The Pile)

Max Activating Token Index: 34

Text #5

Max Range: 0.2931. Min Range: -0.2931

Max Act: 0.2458. Min Act: -0.0000

Data Index: 1012631 (The Pile)

Max Activating Token Index: 186

Text #6

Max Range: 0.2931. Min Range: -0.2931

Max Act: 0.2367. Min Act: -0.0000

Data Index: 572568 (The Pile)

Max Activating Token Index: 729

Text #7

Max Range: 0.2931. Min Range: -0.2931

Max Act: 0.2352. Min Act: -0.0000

Data Index: 1323066 (The Pile)

Max Activating Token Index: 374

Text #8

Max Range: 0.2931. Min Range: -0.2931

Max Act: 0.2396. Min Act: -0.0000

Data Index: 969972 (The Pile)

Max Activating Token Index: 56

Text #9

Max Range: 0.2931. Min Range: -0.2931

Max Act: 0.2281. Min Act: -0.0000

Data Index: 586671 (The Pile)

Max Activating Token Index: 38

Text #10

Max Range: 0.2931. Min Range: -0.2931

Max Act: 0.2330. Min Act: -0.0000

Data Index: 426636 (The Pile)

Max Activating Token Index: 26

Text #11

Max Range: 0.2931. Min Range: -0.2931

Max Act: 0.2391. Min Act: -0.0000

Data Index: 1684953 (The Pile)

Max Activating Token Index: 43

Text #12

Max Range: 0.2931. Min Range: -0.2931

Max Act: 0.2230. Min Act: -0.0000

Data Index: 560844 (The Pile)

Max Activating Token Index: 117

Text #13

Max Range: 0.2931. Min Range: -0.2931

Max Act: 0.2306. Min Act: -0.0000

Data Index: 335894 (The Pile)

Max Activating Token Index: 123

Text #14

Max Range: 0.2931. Min Range: -0.2931

Max Act: 0.2285. Min Act: -0.0000

Data Index: 1485449 (The Pile)

Max Activating Token Index: 801

Text #15

Max Range: 0.2931. Min Range: -0.2931

Max Act: 0.2261. Min Act: -0.0000

Data Index: 981158 (The Pile)

Max Activating Token Index: 299

Text #16

Max Range: 0.2931. Min Range: -0.2931

Max Act: 0.2236. Min Act: -0.0000

Data Index: 1768799 (The Pile)

Max Activating Token Index: 50

Text #17

Max Range: 0.2931. Min Range: -0.2931

Max Act: 0.2210. Min Act: -0.0000

Data Index: 1979555 (The Pile)

Max Activating Token Index: 128

Text #18

Max Range: 0.2931. Min Range: -0.2931

Max Act: 0.2043. Min Act: -0.0000

Data Index: 197442 (The Pile)

Max Activating Token Index: 74

Text #19

Max Range: 0.2931. Min Range: -0.2931

Max Act: 0.2186. Min Act: -0.0000

Data Index: 327481 (The Pile)

Max Activating Token Index: 231