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

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

Neuron 1924 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: 0.9425. Min Range: -0.9425

Max Act: 0.9425. Min Act: -0.0000

Data Index: 1604992 (Python Code)

Max Activating Token Index: 626

Text #1

Max Range: 0.9425. Min Range: -0.9425

Max Act: 0.9080. Min Act: -0.0000

Data Index: 1447265 (Python Code)

Max Activating Token Index: 706

Text #2

Max Range: 0.9425. Min Range: -0.9425

Max Act: 0.8989. Min Act: -0.0000

Data Index: 1652111 (Python Code)

Max Activating Token Index: 550

Text #3

Max Range: 0.9425. Min Range: -0.9425

Max Act: 0.8956. Min Act: -0.0000

Data Index: 1419418 (Python Code)

Max Activating Token Index: 398

Text #4

Max Range: 0.9425. Min Range: -0.9425

Max Act: 0.9000. Min Act: -0.0000

Data Index: 1571004 (Python Code)

Max Activating Token Index: 280

Text #5

Max Range: 0.9425. Min Range: -0.9425

Max Act: 0.8778. Min Act: -0.0000

Data Index: 1436223 (Python Code)

Max Activating Token Index: 176

Text #6

Max Range: 0.9425. Min Range: -0.9425

Max Act: 0.7814. Min Act: -0.0000

Data Index: 1577834 (Python Code)

Max Activating Token Index: 26

Text #7

Max Range: 0.9425. Min Range: -0.9425

Max Act: 0.7237. Min Act: -0.0000

Data Index: 1438015 (Python Code)

Max Activating Token Index: 205

Text #8

Max Range: 0.9425. Min Range: -0.9425

Max Act: 0.7700. Min Act: -0.0000

Data Index: 1468860 (Python Code)

Max Activating Token Index: 976

Text #9

Max Range: 0.9425. Min Range: -0.9425

Max Act: 0.8034. Min Act: -0.0000

Data Index: 1366916 (Python Code)

Max Activating Token Index: 218

Text #10

Max Range: 0.9425. Min Range: -0.9425

Max Act: 0.7633. Min Act: -0.0000

Data Index: 1469143 (Python Code)

Max Activating Token Index: 447

Text #11

Max Range: 0.9425. Min Range: -0.9425

Max Act: 0.7622. Min Act: -0.0000

Data Index: 1544368 (Python Code)

Max Activating Token Index: 572

Text #12

Max Range: 0.9425. Min Range: -0.9425

Max Act: 0.7139. Min Act: -0.0000

Data Index: 1437194 (Python Code)

Max Activating Token Index: 833

Text #13

Max Range: 0.9425. Min Range: -0.9425

Max Act: 0.7335. Min Act: -0.0000

Data Index: 1410770 (Python Code)

Max Activating Token Index: 536

Text #14

Max Range: 0.9425. Min Range: -0.9425

Max Act: 0.7612. Min Act: -0.0000

Data Index: 1630220 (Python Code)

Max Activating Token Index: 58

Text #15

Max Range: 0.9425. Min Range: -0.9425

Max Act: 0.7171. Min Act: -0.0000

Data Index: 1459818 (Python Code)

Max Activating Token Index: 924

Text #16

Max Range: 0.9425. Min Range: -0.9425

Max Act: 0.7352. Min Act: -0.0000

Data Index: 1468321 (Python Code)

Max Activating Token Index: 364

Text #17

Max Range: 0.9425. Min Range: -0.9425

Max Act: 0.7324. Min Act: -0.0000

Data Index: 1426863 (Python Code)

Max Activating Token Index: 978

Text #18

Max Range: 0.9425. Min Range: -0.9425

Max Act: 0.6057. Min Act: -0.0000

Data Index: 1066694 (C4 (Web Text))

Max Activating Token Index: 685

Text #19

Max Range: 0.9425. Min Range: -0.9425

Max Act: 0.6969. Min Act: -0.0000

Data Index: 1401523 (Python Code)

Max Activating Token Index: 746