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

Dataset: The Pile

Neuron 4714 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: 0.4847. Min Range: -0.4847

Max Act: 0.4847. Min Act: -0.0000

Data Index: 780875 (The Pile)

Max Activating Token Index: 399

Text #1

Max Range: 0.4847. Min Range: -0.4847

Max Act: 0.4704. Min Act: -0.0000

Data Index: 1725523 (The Pile)

Max Activating Token Index: 464

Text #2

Max Range: 0.4847. Min Range: -0.4847

Max Act: 0.4296. Min Act: -0.0000

Data Index: 1627539 (The Pile)

Max Activating Token Index: 867

Text #3

Max Range: 0.4847. Min Range: -0.4847

Max Act: 0.4267. Min Act: -0.0000

Data Index: 1694977 (The Pile)

Max Activating Token Index: 598

Text #4

Max Range: 0.4847. Min Range: -0.4847

Max Act: 0.3695. Min Act: -0.0000

Data Index: 1968311 (The Pile)

Max Activating Token Index: 797

Text #5

Max Range: 0.4847. Min Range: -0.4847

Max Act: 0.3619. Min Act: -0.0000

Data Index: 344480 (The Pile)

Max Activating Token Index: 629

Text #6

Max Range: 0.4847. Min Range: -0.4847

Max Act: 0.3979. Min Act: -0.0000

Data Index: 33935 (The Pile)

Max Activating Token Index: 980

Text #7

Max Range: 0.4847. Min Range: -0.4847

Max Act: 0.3221. Min Act: -0.0000

Data Index: 1471820 (The Pile)

Max Activating Token Index: 223

Text #8

Max Range: 0.4847. Min Range: -0.4847

Max Act: 0.2872. Min Act: -0.0000

Data Index: 1008664 (The Pile)

Max Activating Token Index: 367

Text #9

Max Range: 0.4847. Min Range: -0.4847

Max Act: 0.2202. Min Act: -0.0000

Data Index: 181930 (The Pile)

Max Activating Token Index: 1002

Text #10

Max Range: 0.4847. Min Range: -0.4847

Max Act: 0.2866. Min Act: -0.0000

Data Index: 856403 (The Pile)

Max Activating Token Index: 388

Text #11

Max Range: 0.4847. Min Range: -0.4847

Max Act: 0.2508. Min Act: -0.0000

Data Index: 1532128 (The Pile)

Max Activating Token Index: 753

Text #12

Max Range: 0.4847. Min Range: -0.4847

Max Act: 0.2636. Min Act: -0.0000

Data Index: 1156399 (The Pile)

Max Activating Token Index: 602

Text #13

Max Range: 0.4847. Min Range: -0.4847

Max Act: 0.2492. Min Act: -0.0000

Data Index: 772970 (The Pile)

Max Activating Token Index: 919

Text #14

Max Range: 0.4847. Min Range: -0.4847

Max Act: 0.2492. Min Act: -0.0000

Data Index: 1194268 (The Pile)

Max Activating Token Index: 380

Text #15

Max Range: 0.4847. Min Range: -0.4847

Max Act: 0.2427. Min Act: -0.0000

Data Index: 83582 (The Pile)

Max Activating Token Index: 769

Text #16

Max Range: 0.4847. Min Range: -0.4847

Max Act: 0.2421. Min Act: -0.0000

Data Index: 842619 (The Pile)

Max Activating Token Index: 984

Text #17

Max Range: 0.4847. Min Range: -0.4847

Max Act: 0.2505. Min Act: -0.0000

Data Index: 575860 (The Pile)

Max Activating Token Index: 994

Text #18

Max Range: 0.4847. Min Range: -0.4847

Max Act: 0.2595. Min Act: -0.0000

Data Index: 866777 (The Pile)

Max Activating Token Index: 932

Text #19

Max Range: 0.4847. Min Range: -0.4847

Max Act: 0.2122. Min Act: -0.0000

Data Index: 484787 (The Pile)

Max Activating Token Index: 730