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

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

Neuron 1095 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2781. Min Range: -0.2781

Max Act: 0.2781. Min Act: -0.0000

Data Index: 851508 (C4 (Web Text))

Max Activating Token Index: 882

Text #1

Max Range: 0.2781. Min Range: -0.2781

Max Act: 0.2534. Min Act: -0.0000

Data Index: 809892 (C4 (Web Text))

Max Activating Token Index: 961

Text #2

Max Range: 0.2781. Min Range: -0.2781

Max Act: 0.2234. Min Act: -0.0000

Data Index: 848465 (C4 (Web Text))

Max Activating Token Index: 289

Text #3

Max Range: 0.2781. Min Range: -0.2781

Max Act: 0.2146. Min Act: -0.0000

Data Index: 72671 (C4 (Web Text))

Max Activating Token Index: 908

Text #4

Max Range: 0.2781. Min Range: -0.2781

Max Act: 0.2018. Min Act: -0.0000

Data Index: 637588 (C4 (Web Text))

Max Activating Token Index: 857

Text #5

Max Range: 0.2781. Min Range: -0.2781

Max Act: 0.1997. Min Act: -0.0000

Data Index: 1197744 (C4 (Web Text))

Max Activating Token Index: 306

Text #6

Max Range: 0.2781. Min Range: -0.2781

Max Act: 0.2065. Min Act: -0.0000

Data Index: 362736 (C4 (Web Text))

Max Activating Token Index: 253

Text #7

Max Range: 0.2781. Min Range: -0.2781

Max Act: 0.2036. Min Act: -0.0000

Data Index: 221142 (C4 (Web Text))

Max Activating Token Index: 1000

Text #8

Max Range: 0.2781. Min Range: -0.2781

Max Act: 0.1779. Min Act: -0.0000

Data Index: 1220749 (C4 (Web Text))

Max Activating Token Index: 163

Text #9

Max Range: 0.2781. Min Range: -0.2781

Max Act: 0.1789. Min Act: -0.0000

Data Index: 133146 (C4 (Web Text))

Max Activating Token Index: 108

Text #10

Max Range: 0.2781. Min Range: -0.2781

Max Act: 0.1872. Min Act: -0.0000

Data Index: 1268950 (C4 (Web Text))

Max Activating Token Index: 378

Text #11

Max Range: 0.2781. Min Range: -0.2781

Max Act: 0.1862. Min Act: -0.0000

Data Index: 1258939 (C4 (Web Text))

Max Activating Token Index: 807

Text #12

Max Range: 0.2781. Min Range: -0.2781

Max Act: 0.1854. Min Act: -0.0000

Data Index: 1182973 (C4 (Web Text))

Max Activating Token Index: 346

Text #13

Max Range: 0.2781. Min Range: -0.2781

Max Act: 0.1735. Min Act: -0.0000

Data Index: 70491 (C4 (Web Text))

Max Activating Token Index: 463

Text #14

Max Range: 0.2781. Min Range: -0.2781

Max Act: 0.1743. Min Act: -0.0000

Data Index: 387454 (C4 (Web Text))

Max Activating Token Index: 840

Text #15

Max Range: 0.2781. Min Range: -0.2781

Max Act: 0.1762. Min Act: -0.0000

Data Index: 1541534 (Python Code)

Max Activating Token Index: 957

Text #16

Max Range: 0.2781. Min Range: -0.2781

Max Act: 0.1693. Min Act: -0.0000

Data Index: 567789 (C4 (Web Text))

Max Activating Token Index: 915

Text #17

Max Range: 0.2781. Min Range: -0.2781

Max Act: 0.1574. Min Act: -0.0000

Data Index: 41733 (C4 (Web Text))

Max Activating Token Index: 506

Text #18

Max Range: 0.2781. Min Range: -0.2781

Max Act: 0.1605. Min Act: -0.0000

Data Index: 338034 (C4 (Web Text))

Max Activating Token Index: 745

Text #19

Max Range: 0.2781. Min Range: -0.2781

Max Act: 0.1649. Min Act: -0.0000

Data Index: 909781 (C4 (Web Text))

Max Activating Token Index: 997