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

Dataset: The Pile

Neuron 1027 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: 1.1316. Min Range: -1.1316

Max Act: 1.1316. Min Act: -0.0000

Data Index: 925121 (The Pile)

Max Activating Token Index: 41

Text #1

Max Range: 1.1316. Min Range: -1.1316

Max Act: 1.0520. Min Act: -0.0000

Data Index: 1311833 (The Pile)

Max Activating Token Index: 167

Text #2

Max Range: 1.1316. Min Range: -1.1316

Max Act: 0.9002. Min Act: -0.0000

Data Index: 679081 (The Pile)

Max Activating Token Index: 721

Text #3

Max Range: 1.1316. Min Range: -1.1316

Max Act: 0.8870. Min Act: -0.0000

Data Index: 698908 (The Pile)

Max Activating Token Index: 183

Text #4

Max Range: 1.1316. Min Range: -1.1316

Max Act: 0.8422. Min Act: -0.0000

Data Index: 1283043 (The Pile)

Max Activating Token Index: 374

Text #5

Max Range: 1.1316. Min Range: -1.1316

Max Act: 0.8770. Min Act: -0.0000

Data Index: 200663 (The Pile)

Max Activating Token Index: 334

Text #6

Max Range: 1.1316. Min Range: -1.1316

Max Act: 0.8087. Min Act: -0.0000

Data Index: 997824 (The Pile)

Max Activating Token Index: 9

Text #7

Max Range: 1.1316. Min Range: -1.1316

Max Act: 0.8452. Min Act: -0.0000

Data Index: 519917 (The Pile)

Max Activating Token Index: 264

Text #8

Max Range: 1.1316. Min Range: -1.1316

Max Act: 0.7973. Min Act: -0.0000

Data Index: 552427 (The Pile)

Max Activating Token Index: 35

Text #9

Max Range: 1.1316. Min Range: -1.1316

Max Act: 0.8013. Min Act: -0.0000

Data Index: 1556951 (The Pile)

Max Activating Token Index: 963

Text #10

Max Range: 1.1316. Min Range: -1.1316

Max Act: 0.7734. Min Act: -0.0000

Data Index: 472068 (The Pile)

Max Activating Token Index: 174

Text #11

Max Range: 1.1316. Min Range: -1.1316

Max Act: 0.7967. Min Act: -0.0000

Data Index: 856490 (The Pile)

Max Activating Token Index: 291

Text #12

Max Range: 1.1316. Min Range: -1.1316

Max Act: 0.7968. Min Act: -0.0000

Data Index: 269490 (The Pile)

Max Activating Token Index: 399

Text #13

Max Range: 1.1316. Min Range: -1.1316

Max Act: 0.7823. Min Act: -0.0000

Data Index: 1870198 (The Pile)

Max Activating Token Index: 426

Text #14

Max Range: 1.1316. Min Range: -1.1316

Max Act: 0.7806. Min Act: -0.0000

Data Index: 1122604 (The Pile)

Max Activating Token Index: 449

Text #15

Max Range: 1.1316. Min Range: -1.1316

Max Act: 0.7697. Min Act: -0.0000

Data Index: 805072 (The Pile)

Max Activating Token Index: 469

Text #16

Max Range: 1.1316. Min Range: -1.1316

Max Act: 0.7707. Min Act: -0.0000

Data Index: 562447 (The Pile)

Max Activating Token Index: 354

Text #17

Max Range: 1.1316. Min Range: -1.1316

Max Act: 0.7366. Min Act: -0.0000

Data Index: 496298 (The Pile)

Max Activating Token Index: 316

Text #18

Max Range: 1.1316. Min Range: -1.1316

Max Act: 0.7599. Min Act: -0.0000

Data Index: 845270 (The Pile)

Max Activating Token Index: 17

Text #19

Max Range: 1.1316. Min Range: -1.1316

Max Act: 0.7831. Min Act: -0.0000

Data Index: 1271786 (The Pile)

Max Activating Token Index: 50