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

Dataset: The Pile

Neuron 3572 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2781. Min Range: -1.2781

Max Act: 1.2477. Min Act: -0.0000

Data Index: 1961877 (The Pile)

Max Activating Token Index: 254

Text #1

Max Range: 1.2781. Min Range: -1.2781

Max Act: 1.2781. Min Act: -0.0000

Data Index: 1763000 (The Pile)

Max Activating Token Index: 968

Text #2

Max Range: 1.2781. Min Range: -1.2781

Max Act: 1.1771. Min Act: -0.0000

Data Index: 1189706 (The Pile)

Max Activating Token Index: 1013

Text #3

Max Range: 1.2781. Min Range: -1.2781

Max Act: 1.1133. Min Act: -0.0000

Data Index: 1198797 (The Pile)

Max Activating Token Index: 818

Text #4

Max Range: 1.2781. Min Range: -1.2781

Max Act: 1.1282. Min Act: -0.0000

Data Index: 1118971 (The Pile)

Max Activating Token Index: 832

Text #5

Max Range: 1.2781. Min Range: -1.2781

Max Act: 0.9967. Min Act: -0.0000

Data Index: 1543620 (The Pile)

Max Activating Token Index: 196

Text #6

Max Range: 1.2781. Min Range: -1.2781

Max Act: 1.0415. Min Act: -0.0000

Data Index: 1324514 (The Pile)

Max Activating Token Index: 858

Text #7

Max Range: 1.2781. Min Range: -1.2781

Max Act: 1.1452. Min Act: -0.0000

Data Index: 708756 (The Pile)

Max Activating Token Index: 160

Text #8

Max Range: 1.2781. Min Range: -1.2781

Max Act: 1.0028. Min Act: -0.0000

Data Index: 1990849 (The Pile)

Max Activating Token Index: 569

Text #9

Max Range: 1.2781. Min Range: -1.2781

Max Act: 1.0276. Min Act: -0.0000

Data Index: 1745366 (The Pile)

Max Activating Token Index: 702

Text #10

Max Range: 1.2781. Min Range: -1.2781

Max Act: 1.0563. Min Act: -0.0000

Data Index: 1855625 (The Pile)

Max Activating Token Index: 361

Text #11

Max Range: 1.2781. Min Range: -1.2781

Max Act: 0.9936. Min Act: -0.0000

Data Index: 1091208 (The Pile)

Max Activating Token Index: 144

Text #12

Max Range: 1.2781. Min Range: -1.2781

Max Act: 1.0188. Min Act: -0.0000

Data Index: 860906 (The Pile)

Max Activating Token Index: 695

Text #13

Max Range: 1.2781. Min Range: -1.2781

Max Act: 0.8944. Min Act: -0.0000

Data Index: 375892 (The Pile)

Max Activating Token Index: 1010

Text #14

Max Range: 1.2781. Min Range: -1.2781

Max Act: 1.0179. Min Act: -0.0000

Data Index: 962913 (The Pile)

Max Activating Token Index: 418

Text #15

Max Range: 1.2781. Min Range: -1.2781

Max Act: 0.9207. Min Act: -0.0000

Data Index: 261420 (The Pile)

Max Activating Token Index: 405

Text #16

Max Range: 1.2781. Min Range: -1.2781

Max Act: 0.9416. Min Act: -0.0000

Data Index: 326484 (The Pile)

Max Activating Token Index: 692

Text #17

Max Range: 1.2781. Min Range: -1.2781

Max Act: 0.9288. Min Act: -0.0000

Data Index: 499874 (The Pile)

Max Activating Token Index: 186

Text #18

Max Range: 1.2781. Min Range: -1.2781

Max Act: 0.8428. Min Act: -0.0000

Data Index: 745722 (The Pile)

Max Activating Token Index: 674

Text #19

Max Range: 1.2781. Min Range: -1.2781

Max Act: 0.8896. Min Act: -0.0000

Data Index: 844088 (The Pile)

Max Activating Token Index: 358