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

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

Neuron 1058 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9343. Min Range: -1.9343

Max Act: 1.9343. Min Act: -0.0000

Data Index: 1430558 (Python Code)

Max Activating Token Index: 866

Text #1

Max Range: 1.9343. Min Range: -1.9343

Max Act: 1.2652. Min Act: -0.0000

Data Index: 1388437 (Python Code)

Max Activating Token Index: 960

Text #2

Max Range: 1.9343. Min Range: -1.9343

Max Act: 1.1917. Min Act: -0.0000

Data Index: 1487201 (Python Code)

Max Activating Token Index: 277

Text #3

Max Range: 1.9343. Min Range: -1.9343

Max Act: 1.1065. Min Act: -0.0000

Data Index: 491167 (C4 (Web Text))

Max Activating Token Index: 115

Text #4

Max Range: 1.9343. Min Range: -1.9343

Max Act: 1.2104. Min Act: -0.0000

Data Index: 1548678 (Python Code)

Max Activating Token Index: 725

Text #5

Max Range: 1.9343. Min Range: -1.9343

Max Act: 1.1665. Min Act: -0.0000

Data Index: 498732 (C4 (Web Text))

Max Activating Token Index: 512

Text #6

Max Range: 1.9343. Min Range: -1.9343

Max Act: 1.0903. Min Act: -0.0000

Data Index: 513975 (C4 (Web Text))

Max Activating Token Index: 440

Text #7

Max Range: 1.9343. Min Range: -1.9343

Max Act: 1.1161. Min Act: -0.0000

Data Index: 1244705 (C4 (Web Text))

Max Activating Token Index: 53

Text #8

Max Range: 1.9343. Min Range: -1.9343

Max Act: 1.1074. Min Act: -0.0000

Data Index: 1640854 (Python Code)

Max Activating Token Index: 959

Text #9

Max Range: 1.9343. Min Range: -1.9343

Max Act: 1.1955. Min Act: -0.0000

Data Index: 403234 (C4 (Web Text))

Max Activating Token Index: 688

Text #10

Max Range: 1.9343. Min Range: -1.9343

Max Act: 1.0423. Min Act: -0.0000

Data Index: 859823 (C4 (Web Text))

Max Activating Token Index: 82

Text #11

Max Range: 1.9343. Min Range: -1.9343

Max Act: 1.1105. Min Act: -0.0000

Data Index: 1536385 (Python Code)

Max Activating Token Index: 15

Text #12

Max Range: 1.9343. Min Range: -1.9343

Max Act: 1.0773. Min Act: -0.0000

Data Index: 940724 (C4 (Web Text))

Max Activating Token Index: 599

Text #13

Max Range: 1.9343. Min Range: -1.9343

Max Act: 0.9164. Min Act: -0.0000

Data Index: 1375155 (Python Code)

Max Activating Token Index: 829

Text #14

Max Range: 1.9343. Min Range: -1.9343

Max Act: 1.0274. Min Act: -0.0000

Data Index: 168990 (C4 (Web Text))

Max Activating Token Index: 803

Text #15

Max Range: 1.9343. Min Range: -1.9343

Max Act: 1.0919. Min Act: -0.0000

Data Index: 793033 (C4 (Web Text))

Max Activating Token Index: 493

Text #16

Max Range: 1.9343. Min Range: -1.9343

Max Act: 1.0874. Min Act: -0.0000

Data Index: 1533616 (Python Code)

Max Activating Token Index: 736

Text #17

Max Range: 1.9343. Min Range: -1.9343

Max Act: 0.9833. Min Act: -0.0000

Data Index: 1379048 (Python Code)

Max Activating Token Index: 480

Text #18

Max Range: 1.9343. Min Range: -1.9343

Max Act: 1.0140. Min Act: -0.0000

Data Index: 825114 (C4 (Web Text))

Max Activating Token Index: 833

Text #19

Max Range: 1.9343. Min Range: -1.9343

Max Act: 0.9878. Min Act: -0.0000

Data Index: 598994 (C4 (Web Text))

Max Activating Token Index: 289