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

Dataset: The Pile

Neuron 16 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: 0.1999. Min Range: -0.1999

Max Act: 0.1999. Min Act: -0.0000

Data Index: 699573 (The Pile)

Max Activating Token Index: 956

Text #1

Max Range: 0.1999. Min Range: -0.1999

Max Act: 0.1615. Min Act: -0.0000

Data Index: 232483 (The Pile)

Max Activating Token Index: 420

Text #2

Max Range: 0.1999. Min Range: -0.1999

Max Act: 0.1513. Min Act: -0.0000

Data Index: 1421672 (The Pile)

Max Activating Token Index: 516

Text #3

Max Range: 0.1999. Min Range: -0.1999

Max Act: 0.1663. Min Act: -0.0000

Data Index: 293306 (The Pile)

Max Activating Token Index: 409

Text #4

Max Range: 0.1999. Min Range: -0.1999

Max Act: 0.1589. Min Act: -0.0000

Data Index: 1447262 (The Pile)

Max Activating Token Index: 392

Text #5

Max Range: 0.1999. Min Range: -0.1999

Max Act: 0.1480. Min Act: -0.0000

Data Index: 571815 (The Pile)

Max Activating Token Index: 528

Text #6

Max Range: 0.1999. Min Range: -0.1999

Max Act: 0.1194. Min Act: -0.0000

Data Index: 1889991 (The Pile)

Max Activating Token Index: 733

Text #7

Max Range: 0.1999. Min Range: -0.1999

Max Act: 0.1383. Min Act: -0.0000

Data Index: 1994451 (The Pile)

Max Activating Token Index: 365

Text #8

Max Range: 0.1999. Min Range: -0.1999

Max Act: 0.1348. Min Act: -0.0000

Data Index: 684485 (The Pile)

Max Activating Token Index: 350

Text #9

Max Range: 0.1999. Min Range: -0.1999

Max Act: 0.1351. Min Act: -0.0000

Data Index: 1600575 (The Pile)

Max Activating Token Index: 449

Text #10

Max Range: 0.1999. Min Range: -0.1999

Max Act: 0.1525. Min Act: -0.0000

Data Index: 1752685 (The Pile)

Max Activating Token Index: 212

Text #11

Max Range: 0.1999. Min Range: -0.1999

Max Act: 0.1340. Min Act: -0.0000

Data Index: 1633694 (The Pile)

Max Activating Token Index: 91

Text #12

Max Range: 0.1999. Min Range: -0.1999

Max Act: 0.1256. Min Act: -0.0000

Data Index: 1094638 (The Pile)

Max Activating Token Index: 183

Text #13

Max Range: 0.1999. Min Range: -0.1999

Max Act: 0.1157. Min Act: -0.0000

Data Index: 1290931 (The Pile)

Max Activating Token Index: 263

Text #14

Max Range: 0.1999. Min Range: -0.1999

Max Act: 0.1182. Min Act: -0.0000

Data Index: 1183356 (The Pile)

Max Activating Token Index: 286

Text #15

Max Range: 0.1999. Min Range: -0.1999

Max Act: 0.1293. Min Act: -0.0000

Data Index: 1752302 (The Pile)

Max Activating Token Index: 525

Text #16

Max Range: 0.1999. Min Range: -0.1999

Max Act: 0.1163. Min Act: -0.0000

Data Index: 117829 (The Pile)

Max Activating Token Index: 641

Text #17

Max Range: 0.1999. Min Range: -0.1999

Max Act: 0.1123. Min Act: -0.0000

Data Index: 465890 (The Pile)

Max Activating Token Index: 245

Text #18

Max Range: 0.1999. Min Range: -0.1999

Max Act: 0.1284. Min Act: -0.0000

Data Index: 257830 (The Pile)

Max Activating Token Index: 901

Text #19

Max Range: 0.1999. Min Range: -0.1999

Max Act: 0.1185. Min Act: -0.0000

Data Index: 1190305 (The Pile)

Max Activating Token Index: 391