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

Dataset: The Pile

Neuron 3938 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: 3.1233. Min Range: -3.1233

Max Act: 2.9929. Min Act: -0.0000

Data Index: 1204520 (The Pile)

Max Activating Token Index: 190

Text #1

Max Range: 3.1233. Min Range: -3.1233

Max Act: 2.9720. Min Act: -0.0000

Data Index: 356927 (The Pile)

Max Activating Token Index: 497

Text #2

Max Range: 3.1233. Min Range: -3.1233

Max Act: 3.1233. Min Act: -0.0000

Data Index: 1387012 (The Pile)

Max Activating Token Index: 940

Text #3

Max Range: 3.1233. Min Range: -3.1233

Max Act: 3.0005. Min Act: -0.0000

Data Index: 1112445 (The Pile)

Max Activating Token Index: 944

Text #4

Max Range: 3.1233. Min Range: -3.1233

Max Act: 2.9022. Min Act: -0.0000

Data Index: 16763 (The Pile)

Max Activating Token Index: 784

Text #5

Max Range: 3.1233. Min Range: -3.1233

Max Act: 2.7190. Min Act: -0.0000

Data Index: 877300 (The Pile)

Max Activating Token Index: 1021

Text #6

Max Range: 3.1233. Min Range: -3.1233

Max Act: 2.6661. Min Act: -0.0000

Data Index: 1036481 (The Pile)

Max Activating Token Index: 414

Text #7

Max Range: 3.1233. Min Range: -3.1233

Max Act: 2.6003. Min Act: -0.0000

Data Index: 373610 (The Pile)

Max Activating Token Index: 402

Text #8

Max Range: 3.1233. Min Range: -3.1233

Max Act: 2.6101. Min Act: -0.0000

Data Index: 277210 (The Pile)

Max Activating Token Index: 1006

Text #9

Max Range: 3.1233. Min Range: -3.1233

Max Act: 2.6163. Min Act: -0.0000

Data Index: 1919818 (The Pile)

Max Activating Token Index: 198

Text #10

Max Range: 3.1233. Min Range: -3.1233

Max Act: 2.5968. Min Act: -0.0000

Data Index: 1251458 (The Pile)

Max Activating Token Index: 398

Text #11

Max Range: 3.1233. Min Range: -3.1233

Max Act: 2.5892. Min Act: -0.0000

Data Index: 223198 (The Pile)

Max Activating Token Index: 313

Text #12

Max Range: 3.1233. Min Range: -3.1233

Max Act: 2.4746. Min Act: -0.0000

Data Index: 1472180 (The Pile)

Max Activating Token Index: 654

Text #13

Max Range: 3.1233. Min Range: -3.1233

Max Act: 2.4746. Min Act: -0.0000

Data Index: 441820 (The Pile)

Max Activating Token Index: 214

Text #14

Max Range: 3.1233. Min Range: -3.1233

Max Act: 2.1977. Min Act: -0.0000

Data Index: 1207922 (The Pile)

Max Activating Token Index: 962

Text #15

Max Range: 3.1233. Min Range: -3.1233

Max Act: 2.3626. Min Act: -0.0000

Data Index: 1805356 (The Pile)

Max Activating Token Index: 350

Text #16

Max Range: 3.1233. Min Range: -3.1233

Max Act: 2.3705. Min Act: -0.0000

Data Index: 1051930 (The Pile)

Max Activating Token Index: 791

Text #17

Max Range: 3.1233. Min Range: -3.1233

Max Act: 2.2624. Min Act: -0.0000

Data Index: 1239349 (The Pile)

Max Activating Token Index: 155

Text #18

Max Range: 3.1233. Min Range: -3.1233

Max Act: 2.2431. Min Act: -0.0000

Data Index: 722816 (The Pile)

Max Activating Token Index: 597

Text #19

Max Range: 3.1233. Min Range: -3.1233

Max Act: 1.9737. Min Act: -0.0000

Data Index: 1106865 (The Pile)

Max Activating Token Index: 934