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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 5016 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0806. Min Range: -3.0806

Max Act: 3.0806. Min Act: -0.0000

Data Index: 300189 (C4 (Web Text))

Max Activating Token Index: 564

Text #1

Max Range: 3.0806. Min Range: -3.0806

Max Act: 2.2979. Min Act: -0.0000

Data Index: 1067054 (C4 (Web Text))

Max Activating Token Index: 65

Text #2

Max Range: 3.0806. Min Range: -3.0806

Max Act: 2.2867. Min Act: -0.0000

Data Index: 1197017 (C4 (Web Text))

Max Activating Token Index: 422

Text #3

Max Range: 3.0806. Min Range: -3.0806

Max Act: 2.2980. Min Act: -0.0000

Data Index: 473946 (C4 (Web Text))

Max Activating Token Index: 780

Text #4

Max Range: 3.0806. Min Range: -3.0806

Max Act: 2.0757. Min Act: -0.0000

Data Index: 560203 (C4 (Web Text))

Max Activating Token Index: 857

Text #5

Max Range: 3.0806. Min Range: -3.0806

Max Act: 1.9883. Min Act: -0.0000

Data Index: 494003 (C4 (Web Text))

Max Activating Token Index: 505

Text #6

Max Range: 3.0806. Min Range: -3.0806

Max Act: 1.8903. Min Act: -0.0000

Data Index: 1064858 (C4 (Web Text))

Max Activating Token Index: 307

Text #7

Max Range: 3.0806. Min Range: -3.0806

Max Act: 1.7694. Min Act: -0.0000

Data Index: 23880 (C4 (Web Text))

Max Activating Token Index: 289

Text #8

Max Range: 3.0806. Min Range: -3.0806

Max Act: 1.6292. Min Act: -0.0000

Data Index: 12016 (C4 (Web Text))

Max Activating Token Index: 501

Text #9

Max Range: 3.0806. Min Range: -3.0806

Max Act: 1.6109. Min Act: -0.0000

Data Index: 934720 (C4 (Web Text))

Max Activating Token Index: 731

Text #10

Max Range: 3.0806. Min Range: -3.0806

Max Act: 1.5718. Min Act: -0.0000

Data Index: 738970 (C4 (Web Text))

Max Activating Token Index: 873

Text #11

Max Range: 3.0806. Min Range: -3.0806

Max Act: 1.5616. Min Act: -0.0000

Data Index: 276974 (C4 (Web Text))

Max Activating Token Index: 638

Text #12

Max Range: 3.0806. Min Range: -3.0806

Max Act: 1.6020. Min Act: -0.0000

Data Index: 449670 (C4 (Web Text))

Max Activating Token Index: 407

Text #13

Max Range: 3.0806. Min Range: -3.0806

Max Act: 1.5618. Min Act: -0.0000

Data Index: 929857 (C4 (Web Text))

Max Activating Token Index: 176

Text #14

Max Range: 3.0806. Min Range: -3.0806

Max Act: 1.5236. Min Act: -0.0000

Data Index: 826255 (C4 (Web Text))

Max Activating Token Index: 90

Text #15

Max Range: 3.0806. Min Range: -3.0806

Max Act: 1.5297. Min Act: -0.0000

Data Index: 617098 (C4 (Web Text))

Max Activating Token Index: 75

Text #16

Max Range: 3.0806. Min Range: -3.0806

Max Act: 1.4890. Min Act: -0.0000

Data Index: 530808 (C4 (Web Text))

Max Activating Token Index: 326

Text #17

Max Range: 3.0806. Min Range: -3.0806

Max Act: 1.4603. Min Act: -0.0000

Data Index: 592586 (C4 (Web Text))

Max Activating Token Index: 588

Text #18

Max Range: 3.0806. Min Range: -3.0806

Max Act: 1.4234. Min Act: -0.0000

Data Index: 548870 (C4 (Web Text))

Max Activating Token Index: 460

Text #19

Max Range: 3.0806. Min Range: -3.0806

Max Act: 1.4066. Min Act: -0.0000

Data Index: 1337438 (C4 (Web Text))

Max Activating Token Index: 694