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

Dataset: The Pile

Neuron 1749 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: 1.1558. Min Range: -1.1558

Max Act: 1.1558. Min Act: -0.0000

Data Index: 1151045 (The Pile)

Max Activating Token Index: 130

Text #1

Max Range: 1.1558. Min Range: -1.1558

Max Act: 0.9177. Min Act: -0.0000

Data Index: 680869 (The Pile)

Max Activating Token Index: 947

Text #2

Max Range: 1.1558. Min Range: -1.1558

Max Act: 0.9400. Min Act: -0.0000

Data Index: 1804664 (The Pile)

Max Activating Token Index: 27

Text #3

Max Range: 1.1558. Min Range: -1.1558

Max Act: 0.9296. Min Act: -0.0000

Data Index: 1330184 (The Pile)

Max Activating Token Index: 95

Text #4

Max Range: 1.1558. Min Range: -1.1558

Max Act: 0.8481. Min Act: -0.0000

Data Index: 1611001 (The Pile)

Max Activating Token Index: 956

Text #5

Max Range: 1.1558. Min Range: -1.1558

Max Act: 0.7379. Min Act: -0.0000

Data Index: 1977075 (The Pile)

Max Activating Token Index: 464

Text #6

Max Range: 1.1558. Min Range: -1.1558

Max Act: 0.8264. Min Act: -0.0000

Data Index: 1821214 (The Pile)

Max Activating Token Index: 727

Text #7

Max Range: 1.1558. Min Range: -1.1558

Max Act: 0.7329. Min Act: -0.0000

Data Index: 12221 (The Pile)

Max Activating Token Index: 41

Text #8

Max Range: 1.1558. Min Range: -1.1558

Max Act: 0.7291. Min Act: -0.0000

Data Index: 926186 (The Pile)

Max Activating Token Index: 85

Text #9

Max Range: 1.1558. Min Range: -1.1558

Max Act: 0.6649. Min Act: -0.0000

Data Index: 623721 (The Pile)

Max Activating Token Index: 309

Text #10

Max Range: 1.1558. Min Range: -1.1558

Max Act: 0.6791. Min Act: -0.0000

Data Index: 475227 (The Pile)

Max Activating Token Index: 691

Text #11

Max Range: 1.1558. Min Range: -1.1558

Max Act: 0.6525. Min Act: -0.0000

Data Index: 1212231 (The Pile)

Max Activating Token Index: 216

Text #12

Max Range: 1.1558. Min Range: -1.1558

Max Act: 0.6647. Min Act: -0.0000

Data Index: 1534217 (The Pile)

Max Activating Token Index: 811

Text #13

Max Range: 1.1558. Min Range: -1.1558

Max Act: 0.6187. Min Act: -0.0000

Data Index: 1860787 (The Pile)

Max Activating Token Index: 180

Text #14

Max Range: 1.1558. Min Range: -1.1558

Max Act: 0.6540. Min Act: -0.0000

Data Index: 641066 (The Pile)

Max Activating Token Index: 285

Text #15

Max Range: 1.1558. Min Range: -1.1558

Max Act: 0.6341. Min Act: -0.0000

Data Index: 393472 (The Pile)

Max Activating Token Index: 578

Text #16

Max Range: 1.1558. Min Range: -1.1558

Max Act: 0.6489. Min Act: -0.0000

Data Index: 1154449 (The Pile)

Max Activating Token Index: 610

Text #17

Max Range: 1.1558. Min Range: -1.1558

Max Act: 0.6264. Min Act: -0.0000

Data Index: 1637604 (The Pile)

Max Activating Token Index: 242

Text #18

Max Range: 1.1558. Min Range: -1.1558

Max Act: 0.6475. Min Act: -0.0000

Data Index: 1088937 (The Pile)

Max Activating Token Index: 325

Text #19

Max Range: 1.1558. Min Range: -1.1558

Max Act: 0.6157. Min Act: -0.0000

Data Index: 519138 (The Pile)

Max Activating Token Index: 283