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

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

Neuron 4632 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: 5.9850. Min Range: -5.9850

Max Act: 5.9850. Min Act: -0.0001

Data Index: 462163 (C4 (Web Text))

Max Activating Token Index: 496

Text #1

Max Range: 5.9850. Min Range: -5.9850

Max Act: 3.0159. Min Act: -0.0001

Data Index: 209164 (C4 (Web Text))

Max Activating Token Index: 360

Text #2

Max Range: 5.9850. Min Range: -5.9850

Max Act: 2.9872. Min Act: -0.0001

Data Index: 1325393 (C4 (Web Text))

Max Activating Token Index: 733

Text #3

Max Range: 5.9850. Min Range: -5.9850

Max Act: 2.6649. Min Act: -0.0001

Data Index: 406324 (C4 (Web Text))

Max Activating Token Index: 738

Text #4

Max Range: 5.9850. Min Range: -5.9850

Max Act: 2.9700. Min Act: -0.0001

Data Index: 291437 (C4 (Web Text))

Max Activating Token Index: 562

Text #5

Max Range: 5.9850. Min Range: -5.9850

Max Act: 2.6723. Min Act: -0.0001

Data Index: 1332804 (C4 (Web Text))

Max Activating Token Index: 803

Text #6

Max Range: 5.9850. Min Range: -5.9850

Max Act: 2.6575. Min Act: -0.0001

Data Index: 857778 (C4 (Web Text))

Max Activating Token Index: 120

Text #7

Max Range: 5.9850. Min Range: -5.9850

Max Act: 3.1215. Min Act: -0.0001

Data Index: 1034536 (C4 (Web Text))

Max Activating Token Index: 943

Text #8

Max Range: 5.9850. Min Range: -5.9850

Max Act: 2.8086. Min Act: -0.0001

Data Index: 926058 (C4 (Web Text))

Max Activating Token Index: 724

Text #9

Max Range: 5.9850. Min Range: -5.9850

Max Act: 2.9039. Min Act: -0.0001

Data Index: 200627 (C4 (Web Text))

Max Activating Token Index: 344

Text #10

Max Range: 5.9850. Min Range: -5.9850

Max Act: 2.6024. Min Act: -0.0001

Data Index: 262864 (C4 (Web Text))

Max Activating Token Index: 207

Text #11

Max Range: 5.9850. Min Range: -5.9850

Max Act: 2.4663. Min Act: -0.0001

Data Index: 393302 (C4 (Web Text))

Max Activating Token Index: 818

Text #12

Max Range: 5.9850. Min Range: -5.9850

Max Act: 2.8996. Min Act: -0.0001

Data Index: 783835 (C4 (Web Text))

Max Activating Token Index: 227

Text #13

Max Range: 5.9850. Min Range: -5.9850

Max Act: 2.6990. Min Act: -0.0001

Data Index: 635685 (C4 (Web Text))

Max Activating Token Index: 725

Text #14

Max Range: 5.9850. Min Range: -5.9850

Max Act: 2.8245. Min Act: -0.0001

Data Index: 332052 (C4 (Web Text))

Max Activating Token Index: 556

Text #15

Max Range: 5.9850. Min Range: -5.9850

Max Act: 2.5422. Min Act: -0.0001

Data Index: 40926 (C4 (Web Text))

Max Activating Token Index: 516

Text #16

Max Range: 5.9850. Min Range: -5.9850

Max Act: 2.5212. Min Act: -0.0001

Data Index: 186838 (C4 (Web Text))

Max Activating Token Index: 811

Text #17

Max Range: 5.9850. Min Range: -5.9850

Max Act: 2.6298. Min Act: -0.0001

Data Index: 975073 (C4 (Web Text))

Max Activating Token Index: 935

Text #18

Max Range: 5.9850. Min Range: -5.9850

Max Act: 2.6432. Min Act: -0.0001

Data Index: 990758 (C4 (Web Text))

Max Activating Token Index: 113

Text #19

Max Range: 5.9850. Min Range: -5.9850

Max Act: 2.6364. Min Act: -0.0001

Data Index: 18080 (C4 (Web Text))

Max Activating Token Index: 30