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

Dataset: The Pile

Neuron 2984 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9273. Min Range: -3.9273

Max Act: 3.9273. Min Act: -0.0000

Data Index: 885809 (The Pile)

Max Activating Token Index: 663

Text #1

Max Range: 3.9273. Min Range: -3.9273

Max Act: 3.8335. Min Act: -0.0000

Data Index: 1026806 (The Pile)

Max Activating Token Index: 650

Text #2

Max Range: 3.9273. Min Range: -3.9273

Max Act: 3.8365. Min Act: -0.0000

Data Index: 689233 (The Pile)

Max Activating Token Index: 892

Text #3

Max Range: 3.9273. Min Range: -3.9273

Max Act: 3.0269. Min Act: -0.0000

Data Index: 1198891 (The Pile)

Max Activating Token Index: 707

Text #4

Max Range: 3.9273. Min Range: -3.9273

Max Act: 3.2543. Min Act: -0.0000

Data Index: 537466 (The Pile)

Max Activating Token Index: 520

Text #5

Max Range: 3.9273. Min Range: -3.9273

Max Act: 2.8869. Min Act: -0.0000

Data Index: 1238073 (The Pile)

Max Activating Token Index: 459

Text #6

Max Range: 3.9273. Min Range: -3.9273

Max Act: 2.6695. Min Act: -0.0000

Data Index: 1294697 (The Pile)

Max Activating Token Index: 762

Text #7

Max Range: 3.9273. Min Range: -3.9273

Max Act: 2.8216. Min Act: -0.0000

Data Index: 696951 (The Pile)

Max Activating Token Index: 329

Text #8

Max Range: 3.9273. Min Range: -3.9273

Max Act: 2.9781. Min Act: -0.0000

Data Index: 983052 (The Pile)

Max Activating Token Index: 904

Text #9

Max Range: 3.9273. Min Range: -3.9273

Max Act: 2.5674. Min Act: -0.0000

Data Index: 1211764 (The Pile)

Max Activating Token Index: 325

Text #10

Max Range: 3.9273. Min Range: -3.9273

Max Act: 2.3482. Min Act: -0.0000

Data Index: 723923 (The Pile)

Max Activating Token Index: 309

Text #11

Max Range: 3.9273. Min Range: -3.9273

Max Act: 2.2806. Min Act: -0.0000

Data Index: 219665 (The Pile)

Max Activating Token Index: 436

Text #12

Max Range: 3.9273. Min Range: -3.9273

Max Act: 2.1617. Min Act: -0.0000

Data Index: 151405 (The Pile)

Max Activating Token Index: 751

Text #13

Max Range: 3.9273. Min Range: -3.9273

Max Act: 2.3252. Min Act: -0.0000

Data Index: 1143865 (The Pile)

Max Activating Token Index: 960

Text #14

Max Range: 3.9273. Min Range: -3.9273

Max Act: 2.1887. Min Act: -0.0000

Data Index: 343798 (The Pile)

Max Activating Token Index: 620

Text #15

Max Range: 3.9273. Min Range: -3.9273

Max Act: 2.0758. Min Act: -0.0000

Data Index: 1688922 (The Pile)

Max Activating Token Index: 406

Text #16

Max Range: 3.9273. Min Range: -3.9273

Max Act: 2.1778. Min Act: -0.0000

Data Index: 1012614 (The Pile)

Max Activating Token Index: 884

Text #17

Max Range: 3.9273. Min Range: -3.9273

Max Act: 2.0238. Min Act: -0.0000

Data Index: 205536 (The Pile)

Max Activating Token Index: 727

Text #18

Max Range: 3.9273. Min Range: -3.9273

Max Act: 2.2328. Min Act: -0.0000

Data Index: 1417395 (The Pile)

Max Activating Token Index: 829

Text #19

Max Range: 3.9273. Min Range: -3.9273

Max Act: 1.8158. Min Act: -0.0000

Data Index: 770106 (The Pile)

Max Activating Token Index: 892