Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4210 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 4.2822. Min Range: -4.2822

Max Act: 4.2822. Min Act: -0.0001

Data Index: 1146200 (C4 (Web Text))

Max Activating Token Index: 661

Text #1

Max Range: 4.2822. Min Range: -4.2822

Max Act: 3.8646. Min Act: -0.0000

Data Index: 555819 (C4 (Web Text))

Max Activating Token Index: 853

Text #2

Max Range: 4.2822. Min Range: -4.2822

Max Act: 3.7702. Min Act: -0.0001

Data Index: 247800 (C4 (Web Text))

Max Activating Token Index: 813

Text #3

Max Range: 4.2822. Min Range: -4.2822

Max Act: 3.9768. Min Act: -0.0000

Data Index: 476787 (C4 (Web Text))

Max Activating Token Index: 633

Text #4

Max Range: 4.2822. Min Range: -4.2822

Max Act: 3.7813. Min Act: -0.0001

Data Index: 944320 (C4 (Web Text))

Max Activating Token Index: 483

Text #5

Max Range: 4.2822. Min Range: -4.2822

Max Act: 3.9032. Min Act: -0.0001

Data Index: 1042900 (C4 (Web Text))

Max Activating Token Index: 233

Text #6

Max Range: 4.2822. Min Range: -4.2822

Max Act: 3.8875. Min Act: -0.0001

Data Index: 1345605 (C4 (Web Text))

Max Activating Token Index: 350

Text #7

Max Range: 4.2822. Min Range: -4.2822

Max Act: 3.6485. Min Act: -0.0000

Data Index: 715557 (C4 (Web Text))

Max Activating Token Index: 867

Text #8

Max Range: 4.2822. Min Range: -4.2822

Max Act: 3.3298. Min Act: -0.0000

Data Index: 4804 (C4 (Web Text))

Max Activating Token Index: 341

Text #9

Max Range: 4.2822. Min Range: -4.2822

Max Act: 3.7703. Min Act: -0.0001

Data Index: 969991 (C4 (Web Text))

Max Activating Token Index: 403

Text #10

Max Range: 4.2822. Min Range: -4.2822

Max Act: 3.4366. Min Act: -0.0000

Data Index: 540878 (C4 (Web Text))

Max Activating Token Index: 609

Text #11

Max Range: 4.2822. Min Range: -4.2822

Max Act: 3.5741. Min Act: -0.0000

Data Index: 567325 (C4 (Web Text))

Max Activating Token Index: 287

Text #12

Max Range: 4.2822. Min Range: -4.2822

Max Act: 3.8628. Min Act: -0.0000

Data Index: 999595 (C4 (Web Text))

Max Activating Token Index: 819

Text #13

Max Range: 4.2822. Min Range: -4.2822

Max Act: 3.8005. Min Act: -0.0001

Data Index: 695028 (C4 (Web Text))

Max Activating Token Index: 301

Text #14

Max Range: 4.2822. Min Range: -4.2822

Max Act: 3.6278. Min Act: -0.0000

Data Index: 586264 (C4 (Web Text))

Max Activating Token Index: 777

Text #15

Max Range: 4.2822. Min Range: -4.2822

Max Act: 3.2993. Min Act: -0.0001

Data Index: 70883 (C4 (Web Text))

Max Activating Token Index: 347

Text #16

Max Range: 4.2822. Min Range: -4.2822

Max Act: 3.4367. Min Act: -0.0001

Data Index: 1481418 (Python Code)

Max Activating Token Index: 96

Text #17

Max Range: 4.2822. Min Range: -4.2822

Max Act: 3.4279. Min Act: -0.0001

Data Index: 516721 (C4 (Web Text))

Max Activating Token Index: 159

Text #18

Max Range: 4.2822. Min Range: -4.2822

Max Act: 3.4200. Min Act: -0.0001

Data Index: 862578 (C4 (Web Text))

Max Activating Token Index: 822

Text #19

Max Range: 4.2822. Min Range: -4.2822

Max Act: 3.3819. Min Act: -0.0001

Data Index: 993308 (C4 (Web Text))

Max Activating Token Index: 670