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

Dataset: The Pile

Neuron 2985 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4305. Min Range: -1.4305

Max Act: 1.4172. Min Act: -0.0000

Data Index: 1062062 (The Pile)

Max Activating Token Index: 760

Text #1

Max Range: 1.4305. Min Range: -1.4305

Max Act: 1.4020. Min Act: -0.0000

Data Index: 1953793 (The Pile)

Max Activating Token Index: 986

Text #2

Max Range: 1.4305. Min Range: -1.4305

Max Act: 1.4305. Min Act: -0.0000

Data Index: 736560 (The Pile)

Max Activating Token Index: 33

Text #3

Max Range: 1.4305. Min Range: -1.4305

Max Act: 1.2849. Min Act: -0.0000

Data Index: 256093 (The Pile)

Max Activating Token Index: 278

Text #4

Max Range: 1.4305. Min Range: -1.4305

Max Act: 1.2920. Min Act: -0.0000

Data Index: 1589348 (The Pile)

Max Activating Token Index: 126

Text #5

Max Range: 1.4305. Min Range: -1.4305

Max Act: 1.2631. Min Act: -0.0000

Data Index: 1385240 (The Pile)

Max Activating Token Index: 606

Text #6

Max Range: 1.4305. Min Range: -1.4305

Max Act: 1.1840. Min Act: -0.0000

Data Index: 1466246 (The Pile)

Max Activating Token Index: 391

Text #7

Max Range: 1.4305. Min Range: -1.4305

Max Act: 1.2896. Min Act: -0.0000

Data Index: 1411215 (The Pile)

Max Activating Token Index: 515

Text #8

Max Range: 1.4305. Min Range: -1.4305

Max Act: 1.2898. Min Act: -0.0001

Data Index: 253902 (The Pile)

Max Activating Token Index: 390

Text #9

Max Range: 1.4305. Min Range: -1.4305

Max Act: 1.2238. Min Act: -0.0000

Data Index: 1136175 (The Pile)

Max Activating Token Index: 571

Text #10

Max Range: 1.4305. Min Range: -1.4305

Max Act: 1.2100. Min Act: -0.0000

Data Index: 868915 (The Pile)

Max Activating Token Index: 208

Text #11

Max Range: 1.4305. Min Range: -1.4305

Max Act: 1.2441. Min Act: -0.0000

Data Index: 368287 (The Pile)

Max Activating Token Index: 702

Text #12

Max Range: 1.4305. Min Range: -1.4305

Max Act: 1.0657. Min Act: -0.0001

Data Index: 1006527 (The Pile)

Max Activating Token Index: 947

Text #13

Max Range: 1.4305. Min Range: -1.4305

Max Act: 1.1641. Min Act: -0.0000

Data Index: 1914939 (The Pile)

Max Activating Token Index: 797

Text #14

Max Range: 1.4305. Min Range: -1.4305

Max Act: 1.1314. Min Act: -0.0000

Data Index: 1637056 (The Pile)

Max Activating Token Index: 47

Text #15

Max Range: 1.4305. Min Range: -1.4305

Max Act: 1.1593. Min Act: -0.0000

Data Index: 1708695 (The Pile)

Max Activating Token Index: 338

Text #16

Max Range: 1.4305. Min Range: -1.4305

Max Act: 1.0912. Min Act: -0.0000

Data Index: 940901 (The Pile)

Max Activating Token Index: 611

Text #17

Max Range: 1.4305. Min Range: -1.4305

Max Act: 1.0513. Min Act: -0.0000

Data Index: 1222901 (The Pile)

Max Activating Token Index: 744

Text #18

Max Range: 1.4305. Min Range: -1.4305

Max Act: 1.1182. Min Act: -0.0000

Data Index: 356027 (The Pile)

Max Activating Token Index: 245

Text #19

Max Range: 1.4305. Min Range: -1.4305

Max Act: 1.1181. Min Act: -0.0000

Data Index: 1938040 (The Pile)

Max Activating Token Index: 186