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

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

Neuron 2816 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7060. Min Range: -3.7060

Max Act: 3.6969. Min Act: -0.0000

Data Index: 1380844 (Python Code)

Max Activating Token Index: 315

Text #1

Max Range: 3.7060. Min Range: -3.7060

Max Act: 3.7060. Min Act: -0.0000

Data Index: 1401825 (Python Code)

Max Activating Token Index: 341

Text #2

Max Range: 3.7060. Min Range: -3.7060

Max Act: 3.2200. Min Act: -0.0000

Data Index: 1481790 (Python Code)

Max Activating Token Index: 798

Text #3

Max Range: 3.7060. Min Range: -3.7060

Max Act: 3.0287. Min Act: -0.0000

Data Index: 1637424 (Python Code)

Max Activating Token Index: 615

Text #4

Max Range: 3.7060. Min Range: -3.7060

Max Act: 3.0292. Min Act: -0.0000

Data Index: 1565009 (Python Code)

Max Activating Token Index: 885

Text #5

Max Range: 3.7060. Min Range: -3.7060

Max Act: 2.7986. Min Act: -0.0000

Data Index: 1627475 (Python Code)

Max Activating Token Index: 992

Text #6

Max Range: 3.7060. Min Range: -3.7060

Max Act: 2.7787. Min Act: -0.0000

Data Index: 1650903 (Python Code)

Max Activating Token Index: 120

Text #7

Max Range: 3.7060. Min Range: -3.7060

Max Act: 2.9057. Min Act: -0.0000

Data Index: 1475157 (Python Code)

Max Activating Token Index: 694

Text #8

Max Range: 3.7060. Min Range: -3.7060

Max Act: 2.8907. Min Act: -0.0000

Data Index: 1504964 (Python Code)

Max Activating Token Index: 643

Text #9

Max Range: 3.7060. Min Range: -3.7060

Max Act: 2.5853. Min Act: -0.0000

Data Index: 1577785 (Python Code)

Max Activating Token Index: 671

Text #10

Max Range: 3.7060. Min Range: -3.7060

Max Act: 2.4491. Min Act: -0.0000

Data Index: 1441421 (Python Code)

Max Activating Token Index: 264

Text #11

Max Range: 3.7060. Min Range: -3.7060

Max Act: 2.8017. Min Act: -0.0000

Data Index: 1517003 (Python Code)

Max Activating Token Index: 868

Text #12

Max Range: 3.7060. Min Range: -3.7060

Max Act: 2.7737. Min Act: -0.0000

Data Index: 1460685 (Python Code)

Max Activating Token Index: 14

Text #13

Max Range: 3.7060. Min Range: -3.7060

Max Act: 2.7699. Min Act: -0.0000

Data Index: 1522099 (Python Code)

Max Activating Token Index: 747

Text #14

Max Range: 3.7060. Min Range: -3.7060

Max Act: 2.7565. Min Act: -0.0000

Data Index: 1541172 (Python Code)

Max Activating Token Index: 312

Text #15

Max Range: 3.7060. Min Range: -3.7060

Max Act: 2.7493. Min Act: -0.0000

Data Index: 1585313 (Python Code)

Max Activating Token Index: 882

Text #16

Max Range: 3.7060. Min Range: -3.7060

Max Act: 2.7408. Min Act: -0.0000

Data Index: 1583532 (Python Code)

Max Activating Token Index: 124

Text #17

Max Range: 3.7060. Min Range: -3.7060

Max Act: 2.5948. Min Act: -0.0000

Data Index: 1614698 (Python Code)

Max Activating Token Index: 238

Text #18

Max Range: 3.7060. Min Range: -3.7060

Max Act: 2.6809. Min Act: -0.0000

Data Index: 1652695 (Python Code)

Max Activating Token Index: 659

Text #19

Max Range: 3.7060. Min Range: -3.7060

Max Act: 2.8050. Min Act: -0.0000

Data Index: 1462206 (Python Code)

Max Activating Token Index: 877