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

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

Neuron 4095 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2691. Min Range: -2.2691

Max Act: 2.1513. Min Act: -0.0000

Data Index: 37046 (C4 (Web Text))

Max Activating Token Index: 388

Text #1

Max Range: 2.2691. Min Range: -2.2691

Max Act: 2.2038. Min Act: -0.0000

Data Index: 1227230 (C4 (Web Text))

Max Activating Token Index: 614

Text #2

Max Range: 2.2691. Min Range: -2.2691

Max Act: 2.2691. Min Act: -0.0000

Data Index: 210117 (C4 (Web Text))

Max Activating Token Index: 961

Text #3

Max Range: 2.2691. Min Range: -2.2691

Max Act: 2.1438. Min Act: -0.0000

Data Index: 606580 (C4 (Web Text))

Max Activating Token Index: 387

Text #4

Max Range: 2.2691. Min Range: -2.2691

Max Act: 2.0851. Min Act: -0.0000

Data Index: 321659 (C4 (Web Text))

Max Activating Token Index: 858

Text #5

Max Range: 2.2691. Min Range: -2.2691

Max Act: 2.0215. Min Act: -0.0000

Data Index: 562372 (C4 (Web Text))

Max Activating Token Index: 370

Text #6

Max Range: 2.2691. Min Range: -2.2691

Max Act: 1.9974. Min Act: -0.0000

Data Index: 199104 (C4 (Web Text))

Max Activating Token Index: 535

Text #7

Max Range: 2.2691. Min Range: -2.2691

Max Act: 1.9307. Min Act: -0.0000

Data Index: 782707 (C4 (Web Text))

Max Activating Token Index: 610

Text #8

Max Range: 2.2691. Min Range: -2.2691

Max Act: 1.8886. Min Act: -0.0000

Data Index: 1158518 (C4 (Web Text))

Max Activating Token Index: 122

Text #9

Max Range: 2.2691. Min Range: -2.2691

Max Act: 1.9586. Min Act: -0.0000

Data Index: 1354365 (C4 (Web Text))

Max Activating Token Index: 512

Text #10

Max Range: 2.2691. Min Range: -2.2691

Max Act: 1.8908. Min Act: -0.0000

Data Index: 577332 (C4 (Web Text))

Max Activating Token Index: 660

Text #11

Max Range: 2.2691. Min Range: -2.2691

Max Act: 1.8605. Min Act: -0.0000

Data Index: 158681 (C4 (Web Text))

Max Activating Token Index: 534

Text #12

Max Range: 2.2691. Min Range: -2.2691

Max Act: 1.8832. Min Act: -0.0000

Data Index: 70227 (C4 (Web Text))

Max Activating Token Index: 320

Text #13

Max Range: 2.2691. Min Range: -2.2691

Max Act: 1.8630. Min Act: -0.0000

Data Index: 506480 (C4 (Web Text))

Max Activating Token Index: 491

Text #14

Max Range: 2.2691. Min Range: -2.2691

Max Act: 1.9024. Min Act: -0.0000

Data Index: 1065397 (C4 (Web Text))

Max Activating Token Index: 239

Text #15

Max Range: 2.2691. Min Range: -2.2691

Max Act: 1.8233. Min Act: -0.0000

Data Index: 1462678 (Python Code)

Max Activating Token Index: 736

Text #16

Max Range: 2.2691. Min Range: -2.2691

Max Act: 1.8120. Min Act: -0.0000

Data Index: 1111744 (C4 (Web Text))

Max Activating Token Index: 491

Text #17

Max Range: 2.2691. Min Range: -2.2691

Max Act: 1.7076. Min Act: -0.0000

Data Index: 320429 (C4 (Web Text))

Max Activating Token Index: 822

Text #18

Max Range: 2.2691. Min Range: -2.2691

Max Act: 1.7590. Min Act: -0.0000

Data Index: 853514 (C4 (Web Text))

Max Activating Token Index: 81

Text #19

Max Range: 2.2691. Min Range: -2.2691

Max Act: 1.8444. Min Act: -0.0000

Data Index: 1354741 (C4 (Web Text))

Max Activating Token Index: 460