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

Dataset: The Pile

Neuron 293 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: 0.2131. Min Range: -0.2131

Max Act: 0.2131. Min Act: -0.0000

Data Index: 396947 (The Pile)

Max Activating Token Index: 678

Text #1

Max Range: 0.2131. Min Range: -0.2131

Max Act: 0.2083. Min Act: -0.0000

Data Index: 912706 (The Pile)

Max Activating Token Index: 851

Text #2

Max Range: 0.2131. Min Range: -0.2131

Max Act: 0.1939. Min Act: -0.0000

Data Index: 527075 (The Pile)

Max Activating Token Index: 470

Text #3

Max Range: 0.2131. Min Range: -0.2131

Max Act: 0.1702. Min Act: -0.0000

Data Index: 1107510 (The Pile)

Max Activating Token Index: 745

Text #4

Max Range: 0.2131. Min Range: -0.2131

Max Act: 0.1740. Min Act: -0.0000

Data Index: 370669 (The Pile)

Max Activating Token Index: 405

Text #5

Max Range: 0.2131. Min Range: -0.2131

Max Act: 0.1593. Min Act: -0.0000

Data Index: 1321210 (The Pile)

Max Activating Token Index: 766

Text #6

Max Range: 0.2131. Min Range: -0.2131

Max Act: 0.1652. Min Act: -0.0000

Data Index: 912376 (The Pile)

Max Activating Token Index: 67

Text #7

Max Range: 0.2131. Min Range: -0.2131

Max Act: 0.1568. Min Act: -0.0000

Data Index: 1471134 (The Pile)

Max Activating Token Index: 639

Text #8

Max Range: 0.2131. Min Range: -0.2131

Max Act: 0.1521. Min Act: -0.0000

Data Index: 1315751 (The Pile)

Max Activating Token Index: 265

Text #9

Max Range: 0.2131. Min Range: -0.2131

Max Act: 0.1560. Min Act: -0.0000

Data Index: 1131052 (The Pile)

Max Activating Token Index: 540

Text #10

Max Range: 0.2131. Min Range: -0.2131

Max Act: 0.1664. Min Act: -0.0000

Data Index: 1009688 (The Pile)

Max Activating Token Index: 663

Text #11

Max Range: 0.2131. Min Range: -0.2131

Max Act: 0.1438. Min Act: -0.0000

Data Index: 1966955 (The Pile)

Max Activating Token Index: 450

Text #12

Max Range: 0.2131. Min Range: -0.2131

Max Act: 0.1379. Min Act: -0.0000

Data Index: 907532 (The Pile)

Max Activating Token Index: 909

Text #13

Max Range: 0.2131. Min Range: -0.2131

Max Act: 0.1451. Min Act: -0.0000

Data Index: 12268 (The Pile)

Max Activating Token Index: 314

Text #14

Max Range: 0.2131. Min Range: -0.2131

Max Act: 0.1436. Min Act: -0.0000

Data Index: 988233 (The Pile)

Max Activating Token Index: 843

Text #15

Max Range: 0.2131. Min Range: -0.2131

Max Act: 0.1487. Min Act: -0.0000

Data Index: 1749974 (The Pile)

Max Activating Token Index: 103

Text #16

Max Range: 0.2131. Min Range: -0.2131

Max Act: 0.1394. Min Act: -0.0000

Data Index: 1661003 (The Pile)

Max Activating Token Index: 973

Text #17

Max Range: 0.2131. Min Range: -0.2131

Max Act: 0.1315. Min Act: -0.0000

Data Index: 1901066 (The Pile)

Max Activating Token Index: 479

Text #18

Max Range: 0.2131. Min Range: -0.2131

Max Act: 0.1201. Min Act: -0.0000

Data Index: 878789 (The Pile)

Max Activating Token Index: 1003

Text #19

Max Range: 0.2131. Min Range: -0.2131

Max Act: 0.1357. Min Act: -0.0000

Data Index: 929265 (The Pile)

Max Activating Token Index: 956