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

Dataset: The Pile

Neuron 3030 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: 0.2057. Min Range: -0.2057

Max Act: 0.2057. Min Act: -0.0000

Data Index: 1835356 (The Pile)

Max Activating Token Index: 179

Text #1

Max Range: 0.2057. Min Range: -0.2057

Max Act: 0.1899. Min Act: -0.0000

Data Index: 387916 (The Pile)

Max Activating Token Index: 454

Text #2

Max Range: 0.2057. Min Range: -0.2057

Max Act: 0.1705. Min Act: -0.0000

Data Index: 14102 (The Pile)

Max Activating Token Index: 393

Text #3

Max Range: 0.2057. Min Range: -0.2057

Max Act: 0.1532. Min Act: -0.0000

Data Index: 100590 (The Pile)

Max Activating Token Index: 383

Text #4

Max Range: 0.2057. Min Range: -0.2057

Max Act: 0.1542. Min Act: -0.0000

Data Index: 151199 (The Pile)

Max Activating Token Index: 918

Text #5

Max Range: 0.2057. Min Range: -0.2057

Max Act: 0.1514. Min Act: -0.0000

Data Index: 485011 (The Pile)

Max Activating Token Index: 554

Text #6

Max Range: 0.2057. Min Range: -0.2057

Max Act: 0.1294. Min Act: -0.0000

Data Index: 1211173 (The Pile)

Max Activating Token Index: 490

Text #7

Max Range: 0.2057. Min Range: -0.2057

Max Act: 0.1370. Min Act: -0.0000

Data Index: 1433108 (The Pile)

Max Activating Token Index: 377

Text #8

Max Range: 0.2057. Min Range: -0.2057

Max Act: 0.1533. Min Act: -0.0000

Data Index: 1001032 (The Pile)

Max Activating Token Index: 891

Text #9

Max Range: 0.2057. Min Range: -0.2057

Max Act: 0.1407. Min Act: -0.0000

Data Index: 309179 (The Pile)

Max Activating Token Index: 477

Text #10

Max Range: 0.2057. Min Range: -0.2057

Max Act: 0.1425. Min Act: -0.0000

Data Index: 1040814 (The Pile)

Max Activating Token Index: 752

Text #11

Max Range: 0.2057. Min Range: -0.2057

Max Act: 0.1114. Min Act: -0.0000

Data Index: 398279 (The Pile)

Max Activating Token Index: 974

Text #12

Max Range: 0.2057. Min Range: -0.2057

Max Act: 0.1289. Min Act: -0.0000

Data Index: 1431045 (The Pile)

Max Activating Token Index: 525

Text #13

Max Range: 0.2057. Min Range: -0.2057

Max Act: 0.1326. Min Act: -0.0000

Data Index: 1425437 (The Pile)

Max Activating Token Index: 918

Text #14

Max Range: 0.2057. Min Range: -0.2057

Max Act: 0.1225. Min Act: -0.0000

Data Index: 447388 (The Pile)

Max Activating Token Index: 77

Text #15

Max Range: 0.2057. Min Range: -0.2057

Max Act: 0.1224. Min Act: -0.0000

Data Index: 466298 (The Pile)

Max Activating Token Index: 260

Text #16

Max Range: 0.2057. Min Range: -0.2057

Max Act: 0.1253. Min Act: -0.0000

Data Index: 1370373 (The Pile)

Max Activating Token Index: 352

Text #17

Max Range: 0.2057. Min Range: -0.2057

Max Act: 0.1252. Min Act: -0.0000

Data Index: 1345825 (The Pile)

Max Activating Token Index: 407

Text #18

Max Range: 0.2057. Min Range: -0.2057

Max Act: 0.1253. Min Act: -0.0000

Data Index: 165406 (The Pile)

Max Activating Token Index: 272

Text #19

Max Range: 0.2057. Min Range: -0.2057

Max Act: 0.1182. Min Act: -0.0000

Data Index: 159476 (The Pile)

Max Activating Token Index: 178