Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 4082 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.3271. Min Range: -1.3271

Max Act: 1.3271. Min Act: -0.0000

Data Index: 1633706 (The Pile)

Max Activating Token Index: 555

Text #1

Max Range: 1.3271. Min Range: -1.3271

Max Act: 1.1725. Min Act: -0.0000

Data Index: 1153887 (The Pile)

Max Activating Token Index: 859

Text #2

Max Range: 1.3271. Min Range: -1.3271

Max Act: 1.2434. Min Act: -0.0000

Data Index: 1921452 (The Pile)

Max Activating Token Index: 404

Text #3

Max Range: 1.3271. Min Range: -1.3271

Max Act: 1.0201. Min Act: -0.0000

Data Index: 1094960 (The Pile)

Max Activating Token Index: 248

Text #4

Max Range: 1.3271. Min Range: -1.3271

Max Act: 0.9584. Min Act: -0.0000

Data Index: 995303 (The Pile)

Max Activating Token Index: 748

Text #5

Max Range: 1.3271. Min Range: -1.3271

Max Act: 0.9601. Min Act: -0.0000

Data Index: 1110482 (The Pile)

Max Activating Token Index: 401

Text #6

Max Range: 1.3271. Min Range: -1.3271

Max Act: 0.9825. Min Act: -0.0000

Data Index: 1342000 (The Pile)

Max Activating Token Index: 927

Text #7

Max Range: 1.3271. Min Range: -1.3271

Max Act: 0.9869. Min Act: -0.0000

Data Index: 626953 (The Pile)

Max Activating Token Index: 977

Text #8

Max Range: 1.3271. Min Range: -1.3271

Max Act: 0.8918. Min Act: -0.0000

Data Index: 731410 (The Pile)

Max Activating Token Index: 287

Text #9

Max Range: 1.3271. Min Range: -1.3271

Max Act: 0.8875. Min Act: -0.0000

Data Index: 1242175 (The Pile)

Max Activating Token Index: 911

Text #10

Max Range: 1.3271. Min Range: -1.3271

Max Act: 0.9144. Min Act: -0.0000

Data Index: 232136 (The Pile)

Max Activating Token Index: 851

Text #11

Max Range: 1.3271. Min Range: -1.3271

Max Act: 0.8773. Min Act: -0.0000

Data Index: 630947 (The Pile)

Max Activating Token Index: 271

Text #12

Max Range: 1.3271. Min Range: -1.3271

Max Act: 0.8723. Min Act: -0.0000

Data Index: 1520864 (The Pile)

Max Activating Token Index: 548

Text #13

Max Range: 1.3271. Min Range: -1.3271

Max Act: 0.8697. Min Act: -0.0000

Data Index: 836329 (The Pile)

Max Activating Token Index: 603

Text #14

Max Range: 1.3271. Min Range: -1.3271

Max Act: 0.8654. Min Act: 0.0000

Data Index: 375202 (The Pile)

Max Activating Token Index: 918

Text #15

Max Range: 1.3271. Min Range: -1.3271

Max Act: 0.8092. Min Act: -0.0000

Data Index: 305057 (The Pile)

Max Activating Token Index: 229

Text #16

Max Range: 1.3271. Min Range: -1.3271

Max Act: 0.8309. Min Act: -0.0000

Data Index: 1654717 (The Pile)

Max Activating Token Index: 43

Text #17

Max Range: 1.3271. Min Range: -1.3271

Max Act: 0.8554. Min Act: -0.0000

Data Index: 1166558 (The Pile)

Max Activating Token Index: 554

Text #18

Max Range: 1.3271. Min Range: -1.3271

Max Act: 0.7982. Min Act: -0.0000

Data Index: 1282063 (The Pile)

Max Activating Token Index: 508

Text #19

Max Range: 1.3271. Min Range: -1.3271

Max Act: 0.7972. Min Act: -0.0000

Data Index: 97410 (The Pile)

Max Activating Token Index: 483