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

Dataset: The Pile

Neuron 3074 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: 1.0420. Min Range: -1.0420

Max Act: 1.0264. Min Act: -0.0000

Data Index: 1633961 (The Pile)

Max Activating Token Index: 210

Text #1

Max Range: 1.0420. Min Range: -1.0420

Max Act: 1.0420. Min Act: -0.0000

Data Index: 1441805 (The Pile)

Max Activating Token Index: 652

Text #2

Max Range: 1.0420. Min Range: -1.0420

Max Act: 0.8142. Min Act: -0.0000

Data Index: 1160199 (The Pile)

Max Activating Token Index: 25

Text #3

Max Range: 1.0420. Min Range: -1.0420

Max Act: 0.8644. Min Act: -0.0000

Data Index: 1079007 (The Pile)

Max Activating Token Index: 877

Text #4

Max Range: 1.0420. Min Range: -1.0420

Max Act: 0.8550. Min Act: -0.0000

Data Index: 1031250 (The Pile)

Max Activating Token Index: 401

Text #5

Max Range: 1.0420. Min Range: -1.0420

Max Act: 0.8025. Min Act: -0.0000

Data Index: 1885723 (The Pile)

Max Activating Token Index: 606

Text #6

Max Range: 1.0420. Min Range: -1.0420

Max Act: 0.8302. Min Act: -0.0000

Data Index: 106917 (The Pile)

Max Activating Token Index: 475

Text #7

Max Range: 1.0420. Min Range: -1.0420

Max Act: 0.8190. Min Act: -0.0000

Data Index: 1096787 (The Pile)

Max Activating Token Index: 716

Text #8

Max Range: 1.0420. Min Range: -1.0420

Max Act: 0.7290. Min Act: -0.0000

Data Index: 463494 (The Pile)

Max Activating Token Index: 609

Text #9

Max Range: 1.0420. Min Range: -1.0420

Max Act: 0.7806. Min Act: -0.0000

Data Index: 782348 (The Pile)

Max Activating Token Index: 225

Text #10

Max Range: 1.0420. Min Range: -1.0420

Max Act: 0.7659. Min Act: -0.0000

Data Index: 1133502 (The Pile)

Max Activating Token Index: 664

Text #11

Max Range: 1.0420. Min Range: -1.0420

Max Act: 0.8022. Min Act: -0.0000

Data Index: 332784 (The Pile)

Max Activating Token Index: 810

Text #12

Max Range: 1.0420. Min Range: -1.0420

Max Act: 0.7583. Min Act: -0.0000

Data Index: 1802056 (The Pile)

Max Activating Token Index: 109

Text #13

Max Range: 1.0420. Min Range: -1.0420

Max Act: 0.7014. Min Act: -0.0000

Data Index: 214760 (The Pile)

Max Activating Token Index: 299

Text #14

Max Range: 1.0420. Min Range: -1.0420

Max Act: 0.7520. Min Act: -0.0000

Data Index: 859598 (The Pile)

Max Activating Token Index: 548

Text #15

Max Range: 1.0420. Min Range: -1.0420

Max Act: 0.7451. Min Act: -0.0000

Data Index: 980818 (The Pile)

Max Activating Token Index: 281

Text #16

Max Range: 1.0420. Min Range: -1.0420

Max Act: 0.7880. Min Act: -0.0000

Data Index: 1001577 (The Pile)

Max Activating Token Index: 1021

Text #17

Max Range: 1.0420. Min Range: -1.0420

Max Act: 0.6826. Min Act: -0.0000

Data Index: 449427 (The Pile)

Max Activating Token Index: 801

Text #18

Max Range: 1.0420. Min Range: -1.0420

Max Act: 0.7502. Min Act: -0.0000

Data Index: 60533 (The Pile)

Max Activating Token Index: 194

Text #19

Max Range: 1.0420. Min Range: -1.0420

Max Act: 0.7191. Min Act: -0.0000

Data Index: 1512675 (The Pile)

Max Activating Token Index: 242