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

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

Neuron 588 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: 3.6078. Min Range: -3.6078

Max Act: 3.6078. Min Act: -0.0000

Data Index: 1584894 (Python Code)

Max Activating Token Index: 819

Text #1

Max Range: 3.6078. Min Range: -3.6078

Max Act: 3.3066. Min Act: -0.0000

Data Index: 1645195 (Python Code)

Max Activating Token Index: 860

Text #2

Max Range: 3.6078. Min Range: -3.6078

Max Act: 3.4155. Min Act: -0.0000

Data Index: 1458846 (Python Code)

Max Activating Token Index: 854

Text #3

Max Range: 3.6078. Min Range: -3.6078

Max Act: 3.3671. Min Act: -0.0000

Data Index: 1442397 (Python Code)

Max Activating Token Index: 341

Text #4

Max Range: 3.6078. Min Range: -3.6078

Max Act: 2.9451. Min Act: -0.0000

Data Index: 1497276 (Python Code)

Max Activating Token Index: 577

Text #5

Max Range: 3.6078. Min Range: -3.6078

Max Act: 2.6799. Min Act: -0.0000

Data Index: 1530636 (Python Code)

Max Activating Token Index: 952

Text #6

Max Range: 3.6078. Min Range: -3.6078

Max Act: 3.1453. Min Act: -0.0000

Data Index: 1654809 (Python Code)

Max Activating Token Index: 188

Text #7

Max Range: 3.6078. Min Range: -3.6078

Max Act: 2.8305. Min Act: -0.0000

Data Index: 1597694 (Python Code)

Max Activating Token Index: 839

Text #8

Max Range: 3.6078. Min Range: -3.6078

Max Act: 2.8073. Min Act: -0.0000

Data Index: 1448342 (Python Code)

Max Activating Token Index: 79

Text #9

Max Range: 3.6078. Min Range: -3.6078

Max Act: 2.8467. Min Act: -0.0000

Data Index: 1544731 (Python Code)

Max Activating Token Index: 574

Text #10

Max Range: 3.6078. Min Range: -3.6078

Max Act: 2.4982. Min Act: -0.0000

Data Index: 1386461 (Python Code)

Max Activating Token Index: 771

Text #11

Max Range: 3.6078. Min Range: -3.6078

Max Act: 2.7466. Min Act: -0.0000

Data Index: 1652722 (Python Code)

Max Activating Token Index: 90

Text #12

Max Range: 3.6078. Min Range: -3.6078

Max Act: 2.4306. Min Act: -0.0000

Data Index: 1552757 (Python Code)

Max Activating Token Index: 889

Text #13

Max Range: 3.6078. Min Range: -3.6078

Max Act: 2.6982. Min Act: -0.0000

Data Index: 1477555 (Python Code)

Max Activating Token Index: 935

Text #14

Max Range: 3.6078. Min Range: -3.6078

Max Act: 2.7048. Min Act: -0.0000

Data Index: 1463367 (Python Code)

Max Activating Token Index: 238

Text #15

Max Range: 3.6078. Min Range: -3.6078

Max Act: 2.6468. Min Act: -0.0000

Data Index: 1378334 (Python Code)

Max Activating Token Index: 160

Text #16

Max Range: 3.6078. Min Range: -3.6078

Max Act: 2.3496. Min Act: -0.0000

Data Index: 1651864 (Python Code)

Max Activating Token Index: 430

Text #17

Max Range: 3.6078. Min Range: -3.6078

Max Act: 2.5546. Min Act: -0.0000

Data Index: 1474911 (Python Code)

Max Activating Token Index: 677

Text #18

Max Range: 3.6078. Min Range: -3.6078

Max Act: 2.3048. Min Act: -0.0000

Data Index: 1429792 (Python Code)

Max Activating Token Index: 575

Text #19

Max Range: 3.6078. Min Range: -3.6078

Max Act: 2.1211. Min Act: -0.0000

Data Index: 1651253 (Python Code)

Max Activating Token Index: 852