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

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

Neuron 411 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4832. Min Range: -0.4832

Max Act: 0.4832. Min Act: -0.0000

Data Index: 1229295 (C4 (Web Text))

Max Activating Token Index: 417

Text #1

Max Range: 0.4832. Min Range: -0.4832

Max Act: 0.3721. Min Act: -0.0000

Data Index: 553874 (C4 (Web Text))

Max Activating Token Index: 987

Text #2

Max Range: 0.4832. Min Range: -0.4832

Max Act: 0.3304. Min Act: -0.0000

Data Index: 620013 (C4 (Web Text))

Max Activating Token Index: 577

Text #3

Max Range: 0.4832. Min Range: -0.4832

Max Act: 0.2776. Min Act: -0.0000

Data Index: 1055386 (C4 (Web Text))

Max Activating Token Index: 294

Text #4

Max Range: 0.4832. Min Range: -0.4832

Max Act: 0.2655. Min Act: 0.0000

Data Index: 808042 (C4 (Web Text))

Max Activating Token Index: 475

Text #5

Max Range: 0.4832. Min Range: -0.4832

Max Act: 0.2521. Min Act: -0.0000

Data Index: 1281237 (C4 (Web Text))

Max Activating Token Index: 418

Text #6

Max Range: 0.4832. Min Range: -0.4832

Max Act: 0.2077. Min Act: -0.0000

Data Index: 200227 (C4 (Web Text))

Max Activating Token Index: 116

Text #7

Max Range: 0.4832. Min Range: -0.4832

Max Act: 0.2081. Min Act: -0.0000

Data Index: 1160286 (C4 (Web Text))

Max Activating Token Index: 655

Text #8

Max Range: 0.4832. Min Range: -0.4832

Max Act: 0.1899. Min Act: -0.0000

Data Index: 1057340 (C4 (Web Text))

Max Activating Token Index: 43

Text #9

Max Range: 0.4832. Min Range: -0.4832

Max Act: 0.1757. Min Act: -0.0000

Data Index: 639119 (C4 (Web Text))

Max Activating Token Index: 68

Text #10

Max Range: 0.4832. Min Range: -0.4832

Max Act: 0.1868. Min Act: -0.0000

Data Index: 104641 (C4 (Web Text))

Max Activating Token Index: 502

Text #11

Max Range: 0.4832. Min Range: -0.4832

Max Act: 0.1705. Min Act: 0.0000

Data Index: 889156 (C4 (Web Text))

Max Activating Token Index: 20

Text #12

Max Range: 0.4832. Min Range: -0.4832

Max Act: 0.1752. Min Act: -0.0000

Data Index: 831508 (C4 (Web Text))

Max Activating Token Index: 166

Text #13

Max Range: 0.4832. Min Range: -0.4832

Max Act: 0.1631. Min Act: 0.0000

Data Index: 1286641 (C4 (Web Text))

Max Activating Token Index: 533

Text #14

Max Range: 0.4832. Min Range: -0.4832

Max Act: 0.1443. Min Act: -0.0000

Data Index: 1547020 (Python Code)

Max Activating Token Index: 847

Text #15

Max Range: 0.4832. Min Range: -0.4832

Max Act: 0.1403. Min Act: -0.0000

Data Index: 104821 (C4 (Web Text))

Max Activating Token Index: 242

Text #16

Max Range: 0.4832. Min Range: -0.4832

Max Act: 0.1585. Min Act: -0.0000

Data Index: 837531 (C4 (Web Text))

Max Activating Token Index: 977

Text #17

Max Range: 0.4832. Min Range: -0.4832

Max Act: 0.1426. Min Act: -0.0000

Data Index: 1181897 (C4 (Web Text))

Max Activating Token Index: 1008

Text #18

Max Range: 0.4832. Min Range: -0.4832

Max Act: 0.1437. Min Act: -0.0000

Data Index: 893694 (C4 (Web Text))

Max Activating Token Index: 275

Text #19

Max Range: 0.4832. Min Range: -0.4832

Max Act: 0.1456. Min Act: -0.0000

Data Index: 1322104 (C4 (Web Text))

Max Activating Token Index: 341