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

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

Neuron 1783 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8303. Min Range: -2.8303

Max Act: 2.8303. Min Act: -0.0000

Data Index: 468136 (C4 (Web Text))

Max Activating Token Index: 707

Text #1

Max Range: 2.8303. Min Range: -2.8303

Max Act: 1.9696. Min Act: -0.0000

Data Index: 1097346 (C4 (Web Text))

Max Activating Token Index: 399

Text #2

Max Range: 2.8303. Min Range: -2.8303

Max Act: 1.5280. Min Act: -0.0000

Data Index: 247925 (C4 (Web Text))

Max Activating Token Index: 356

Text #3

Max Range: 2.8303. Min Range: -2.8303

Max Act: 1.8110. Min Act: -0.0000

Data Index: 615948 (C4 (Web Text))

Max Activating Token Index: 350

Text #4

Max Range: 2.8303. Min Range: -2.8303

Max Act: 1.4759. Min Act: -0.0000

Data Index: 833472 (C4 (Web Text))

Max Activating Token Index: 977

Text #5

Max Range: 2.8303. Min Range: -2.8303

Max Act: 1.4773. Min Act: -0.0000

Data Index: 849134 (C4 (Web Text))

Max Activating Token Index: 949

Text #6

Max Range: 2.8303. Min Range: -2.8303

Max Act: 1.1758. Min Act: -0.0000

Data Index: 810575 (C4 (Web Text))

Max Activating Token Index: 834

Text #7

Max Range: 2.8303. Min Range: -2.8303

Max Act: 1.2173. Min Act: -0.0000

Data Index: 1056360 (C4 (Web Text))

Max Activating Token Index: 311

Text #8

Max Range: 2.8303. Min Range: -2.8303

Max Act: 1.2444. Min Act: -0.0000

Data Index: 366312 (C4 (Web Text))

Max Activating Token Index: 884

Text #9

Max Range: 2.8303. Min Range: -2.8303

Max Act: 1.2140. Min Act: -0.0000

Data Index: 530245 (C4 (Web Text))

Max Activating Token Index: 890

Text #10

Max Range: 2.8303. Min Range: -2.8303

Max Act: 1.2195. Min Act: -0.0000

Data Index: 560708 (C4 (Web Text))

Max Activating Token Index: 555

Text #11

Max Range: 2.8303. Min Range: -2.8303

Max Act: 1.2680. Min Act: -0.0000

Data Index: 647805 (C4 (Web Text))

Max Activating Token Index: 638

Text #12

Max Range: 2.8303. Min Range: -2.8303

Max Act: 1.1712. Min Act: -0.0000

Data Index: 1032555 (C4 (Web Text))

Max Activating Token Index: 529

Text #13

Max Range: 2.8303. Min Range: -2.8303

Max Act: 1.0253. Min Act: -0.0000

Data Index: 608877 (C4 (Web Text))

Max Activating Token Index: 553

Text #14

Max Range: 2.8303. Min Range: -2.8303

Max Act: 1.0904. Min Act: -0.0000

Data Index: 514551 (C4 (Web Text))

Max Activating Token Index: 280

Text #15

Max Range: 2.8303. Min Range: -2.8303

Max Act: 1.0839. Min Act: -0.0000

Data Index: 424958 (C4 (Web Text))

Max Activating Token Index: 932

Text #16

Max Range: 2.8303. Min Range: -2.8303

Max Act: 1.1487. Min Act: -0.0000

Data Index: 1295704 (C4 (Web Text))

Max Activating Token Index: 601

Text #17

Max Range: 2.8303. Min Range: -2.8303

Max Act: 0.9987. Min Act: -0.0000

Data Index: 975807 (C4 (Web Text))

Max Activating Token Index: 685

Text #18

Max Range: 2.8303. Min Range: -2.8303

Max Act: 1.0447. Min Act: -0.0000

Data Index: 389116 (C4 (Web Text))

Max Activating Token Index: 878

Text #19

Max Range: 2.8303. Min Range: -2.8303

Max Act: 1.0325. Min Act: -0.0000

Data Index: 118591 (C4 (Web Text))

Max Activating Token Index: 633