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

Dataset: The Pile

Neuron 921 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2762. Min Range: -1.2762

Max Act: 1.2762. Min Act: -0.0000

Data Index: 1936298 (The Pile)

Max Activating Token Index: 85

Text #1

Max Range: 1.2762. Min Range: -1.2762

Max Act: 1.1456. Min Act: -0.0000

Data Index: 814251 (The Pile)

Max Activating Token Index: 602

Text #2

Max Range: 1.2762. Min Range: -1.2762

Max Act: 1.1385. Min Act: -0.0000

Data Index: 1152531 (The Pile)

Max Activating Token Index: 789

Text #3

Max Range: 1.2762. Min Range: -1.2762

Max Act: 1.0971. Min Act: -0.0000

Data Index: 575118 (The Pile)

Max Activating Token Index: 268

Text #4

Max Range: 1.2762. Min Range: -1.2762

Max Act: 1.1006. Min Act: -0.0000

Data Index: 803335 (The Pile)

Max Activating Token Index: 516

Text #5

Max Range: 1.2762. Min Range: -1.2762

Max Act: 1.0774. Min Act: -0.0000

Data Index: 546520 (The Pile)

Max Activating Token Index: 389

Text #6

Max Range: 1.2762. Min Range: -1.2762

Max Act: 1.0525. Min Act: -0.0000

Data Index: 1109691 (The Pile)

Max Activating Token Index: 209

Text #7

Max Range: 1.2762. Min Range: -1.2762

Max Act: 1.0426. Min Act: -0.0000

Data Index: 572869 (The Pile)

Max Activating Token Index: 335

Text #8

Max Range: 1.2762. Min Range: -1.2762

Max Act: 1.0290. Min Act: -0.0000

Data Index: 328999 (The Pile)

Max Activating Token Index: 47

Text #9

Max Range: 1.2762. Min Range: -1.2762

Max Act: 1.0618. Min Act: -0.0000

Data Index: 154931 (The Pile)

Max Activating Token Index: 882

Text #10

Max Range: 1.2762. Min Range: -1.2762

Max Act: 1.0229. Min Act: -0.0000

Data Index: 1793265 (The Pile)

Max Activating Token Index: 735

Text #11

Max Range: 1.2762. Min Range: -1.2762

Max Act: 1.0257. Min Act: -0.0000

Data Index: 851342 (The Pile)

Max Activating Token Index: 275

Text #12

Max Range: 1.2762. Min Range: -1.2762

Max Act: 0.9621. Min Act: -0.0000

Data Index: 766057 (The Pile)

Max Activating Token Index: 808

Text #13

Max Range: 1.2762. Min Range: -1.2762

Max Act: 0.9659. Min Act: -0.0000

Data Index: 1173868 (The Pile)

Max Activating Token Index: 314

Text #14

Max Range: 1.2762. Min Range: -1.2762

Max Act: 0.9653. Min Act: -0.0000

Data Index: 840028 (The Pile)

Max Activating Token Index: 670

Text #15

Max Range: 1.2762. Min Range: -1.2762

Max Act: 1.0120. Min Act: -0.0000

Data Index: 1771850 (The Pile)

Max Activating Token Index: 21

Text #16

Max Range: 1.2762. Min Range: -1.2762

Max Act: 0.9341. Min Act: -0.0000

Data Index: 1309702 (The Pile)

Max Activating Token Index: 406

Text #17

Max Range: 1.2762. Min Range: -1.2762

Max Act: 0.8850. Min Act: -0.0000

Data Index: 1394118 (The Pile)

Max Activating Token Index: 923

Text #18

Max Range: 1.2762. Min Range: -1.2762

Max Act: 0.9305. Min Act: -0.0000

Data Index: 919550 (The Pile)

Max Activating Token Index: 540

Text #19

Max Range: 1.2762. Min Range: -1.2762

Max Act: 0.8613. Min Act: -0.0000

Data Index: 526879 (The Pile)

Max Activating Token Index: 50