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

Dataset: The Pile

Neuron 238 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.2410. Min Range: -1.2410

Max Act: 1.2410. Min Act: -0.0000

Data Index: 1482526 (The Pile)

Max Activating Token Index: 477

Text #1

Max Range: 1.2410. Min Range: -1.2410

Max Act: 1.1597. Min Act: -0.0000

Data Index: 251731 (The Pile)

Max Activating Token Index: 318

Text #2

Max Range: 1.2410. Min Range: -1.2410

Max Act: 1.1569. Min Act: -0.0000

Data Index: 1928721 (The Pile)

Max Activating Token Index: 242

Text #3

Max Range: 1.2410. Min Range: -1.2410

Max Act: 1.1188. Min Act: -0.0000

Data Index: 1352135 (The Pile)

Max Activating Token Index: 254

Text #4

Max Range: 1.2410. Min Range: -1.2410

Max Act: 1.0433. Min Act: -0.0000

Data Index: 660099 (The Pile)

Max Activating Token Index: 204

Text #5

Max Range: 1.2410. Min Range: -1.2410

Max Act: 1.0375. Min Act: -0.0000

Data Index: 340395 (The Pile)

Max Activating Token Index: 275

Text #6

Max Range: 1.2410. Min Range: -1.2410

Max Act: 1.0189. Min Act: -0.0000

Data Index: 26277 (The Pile)

Max Activating Token Index: 242

Text #7

Max Range: 1.2410. Min Range: -1.2410

Max Act: 1.0125. Min Act: -0.0000

Data Index: 1628489 (The Pile)

Max Activating Token Index: 66

Text #8

Max Range: 1.2410. Min Range: -1.2410

Max Act: 1.0134. Min Act: -0.0000

Data Index: 1744049 (The Pile)

Max Activating Token Index: 449

Text #9

Max Range: 1.2410. Min Range: -1.2410

Max Act: 0.9136. Min Act: -0.0000

Data Index: 1473575 (The Pile)

Max Activating Token Index: 553

Text #10

Max Range: 1.2410. Min Range: -1.2410

Max Act: 0.9156. Min Act: -0.0000

Data Index: 309651 (The Pile)

Max Activating Token Index: 794

Text #11

Max Range: 1.2410. Min Range: -1.2410

Max Act: 0.8446. Min Act: -0.0000

Data Index: 828932 (The Pile)

Max Activating Token Index: 245

Text #12

Max Range: 1.2410. Min Range: -1.2410

Max Act: 0.8444. Min Act: -0.0000

Data Index: 808518 (The Pile)

Max Activating Token Index: 59

Text #13

Max Range: 1.2410. Min Range: -1.2410

Max Act: 0.8634. Min Act: -0.0000

Data Index: 877880 (The Pile)

Max Activating Token Index: 393

Text #14

Max Range: 1.2410. Min Range: -1.2410

Max Act: 0.8752. Min Act: -0.0000

Data Index: 1455748 (The Pile)

Max Activating Token Index: 989

Text #15

Max Range: 1.2410. Min Range: -1.2410

Max Act: 0.8302. Min Act: -0.0000

Data Index: 1790131 (The Pile)

Max Activating Token Index: 470

Text #16

Max Range: 1.2410. Min Range: -1.2410

Max Act: 0.8568. Min Act: -0.0000

Data Index: 516554 (The Pile)

Max Activating Token Index: 229

Text #17

Max Range: 1.2410. Min Range: -1.2410

Max Act: 0.8264. Min Act: -0.0000

Data Index: 119590 (The Pile)

Max Activating Token Index: 810

Text #18

Max Range: 1.2410. Min Range: -1.2410

Max Act: 0.9144. Min Act: -0.0000

Data Index: 11340 (The Pile)

Max Activating Token Index: 915

Text #19

Max Range: 1.2410. Min Range: -1.2410

Max Act: 0.7507. Min Act: -0.0000

Data Index: 497718 (The Pile)

Max Activating Token Index: 261