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

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

Neuron 3330 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: 1.1781. Min Range: -1.1781

Max Act: 1.1781. Min Act: -0.0001

Data Index: 1312507 (C4 (Web Text))

Max Activating Token Index: 236

Text #1

Max Range: 1.1781. Min Range: -1.1781

Max Act: 1.1376. Min Act: -0.0001

Data Index: 94485 (C4 (Web Text))

Max Activating Token Index: 749

Text #2

Max Range: 1.1781. Min Range: -1.1781

Max Act: 1.0680. Min Act: -0.0001

Data Index: 172774 (C4 (Web Text))

Max Activating Token Index: 214

Text #3

Max Range: 1.1781. Min Range: -1.1781

Max Act: 1.0637. Min Act: -0.0001

Data Index: 488922 (C4 (Web Text))

Max Activating Token Index: 137

Text #4

Max Range: 1.1781. Min Range: -1.1781

Max Act: 1.0609. Min Act: -0.0001

Data Index: 525149 (C4 (Web Text))

Max Activating Token Index: 888

Text #5

Max Range: 1.1781. Min Range: -1.1781

Max Act: 1.0202. Min Act: -0.0001

Data Index: 927594 (C4 (Web Text))

Max Activating Token Index: 420

Text #6

Max Range: 1.1781. Min Range: -1.1781

Max Act: 0.9880. Min Act: -0.0001

Data Index: 1024121 (C4 (Web Text))

Max Activating Token Index: 763

Text #7

Max Range: 1.1781. Min Range: -1.1781

Max Act: 1.0152. Min Act: -0.0001

Data Index: 56884 (C4 (Web Text))

Max Activating Token Index: 925

Text #8

Max Range: 1.1781. Min Range: -1.1781

Max Act: 1.0206. Min Act: -0.0001

Data Index: 1269031 (C4 (Web Text))

Max Activating Token Index: 567

Text #9

Max Range: 1.1781. Min Range: -1.1781

Max Act: 1.0823. Min Act: -0.0001

Data Index: 139785 (C4 (Web Text))

Max Activating Token Index: 67

Text #10

Max Range: 1.1781. Min Range: -1.1781

Max Act: 0.9514. Min Act: -0.0001

Data Index: 362341 (C4 (Web Text))

Max Activating Token Index: 92

Text #11

Max Range: 1.1781. Min Range: -1.1781

Max Act: 0.9652. Min Act: -0.0001

Data Index: 492162 (C4 (Web Text))

Max Activating Token Index: 414

Text #12

Max Range: 1.1781. Min Range: -1.1781

Max Act: 0.9734. Min Act: -0.0001

Data Index: 265554 (C4 (Web Text))

Max Activating Token Index: 898

Text #13

Max Range: 1.1781. Min Range: -1.1781

Max Act: 0.9729. Min Act: -0.0001

Data Index: 754638 (C4 (Web Text))

Max Activating Token Index: 574

Text #14

Max Range: 1.1781. Min Range: -1.1781

Max Act: 0.9628. Min Act: -0.0001

Data Index: 1153219 (C4 (Web Text))

Max Activating Token Index: 619

Text #15

Max Range: 1.1781. Min Range: -1.1781

Max Act: 0.9555. Min Act: -0.0001

Data Index: 1109240 (C4 (Web Text))

Max Activating Token Index: 776

Text #16

Max Range: 1.1781. Min Range: -1.1781

Max Act: 0.8899. Min Act: -0.0001

Data Index: 262573 (C4 (Web Text))

Max Activating Token Index: 710

Text #17

Max Range: 1.1781. Min Range: -1.1781

Max Act: 0.8698. Min Act: -0.0001

Data Index: 207236 (C4 (Web Text))

Max Activating Token Index: 609

Text #18

Max Range: 1.1781. Min Range: -1.1781

Max Act: 0.8695. Min Act: -0.0001

Data Index: 343890 (C4 (Web Text))

Max Activating Token Index: 1017

Text #19

Max Range: 1.1781. Min Range: -1.1781

Max Act: 0.8931. Min Act: -0.0001

Data Index: 1266876 (C4 (Web Text))

Max Activating Token Index: 6