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

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

Neuron 3414 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5080. Min Range: -1.5080

Max Act: 1.5080. Min Act: -0.0000

Data Index: 30625 (C4 (Web Text))

Max Activating Token Index: 924

Text #1

Max Range: 1.5080. Min Range: -1.5080

Max Act: 1.0560. Min Act: -0.0000

Data Index: 646483 (C4 (Web Text))

Max Activating Token Index: 651

Text #2

Max Range: 1.5080. Min Range: -1.5080

Max Act: 0.9158. Min Act: -0.0000

Data Index: 861278 (C4 (Web Text))

Max Activating Token Index: 619

Text #3

Max Range: 1.5080. Min Range: -1.5080

Max Act: 0.8021. Min Act: -0.0000

Data Index: 1437200 (Python Code)

Max Activating Token Index: 586

Text #4

Max Range: 1.5080. Min Range: -1.5080

Max Act: 0.7162. Min Act: -0.0000

Data Index: 1477549 (Python Code)

Max Activating Token Index: 936

Text #5

Max Range: 1.5080. Min Range: -1.5080

Max Act: 0.7425. Min Act: -0.0000

Data Index: 340998 (C4 (Web Text))

Max Activating Token Index: 972

Text #6

Max Range: 1.5080. Min Range: -1.5080

Max Act: 0.6597. Min Act: -0.0000

Data Index: 190001 (C4 (Web Text))

Max Activating Token Index: 438

Text #7

Max Range: 1.5080. Min Range: -1.5080

Max Act: 0.7014. Min Act: -0.0000

Data Index: 1646564 (Python Code)

Max Activating Token Index: 751

Text #8

Max Range: 1.5080. Min Range: -1.5080

Max Act: 0.6755. Min Act: -0.0000

Data Index: 1629234 (Python Code)

Max Activating Token Index: 698

Text #9

Max Range: 1.5080. Min Range: -1.5080

Max Act: 0.6032. Min Act: -0.0000

Data Index: 1501908 (Python Code)

Max Activating Token Index: 562

Text #10

Max Range: 1.5080. Min Range: -1.5080

Max Act: 0.6642. Min Act: -0.0000

Data Index: 1631481 (Python Code)

Max Activating Token Index: 28

Text #11

Max Range: 1.5080. Min Range: -1.5080

Max Act: 0.6174. Min Act: -0.0000

Data Index: 1592707 (Python Code)

Max Activating Token Index: 104

Text #12

Max Range: 1.5080. Min Range: -1.5080

Max Act: 0.5747. Min Act: -0.0000

Data Index: 1443172 (Python Code)

Max Activating Token Index: 233

Text #13

Max Range: 1.5080. Min Range: -1.5080

Max Act: 0.5550. Min Act: -0.0000

Data Index: 1633939 (Python Code)

Max Activating Token Index: 438

Text #14

Max Range: 1.5080. Min Range: -1.5080

Max Act: 0.5834. Min Act: -0.0000

Data Index: 1580808 (Python Code)

Max Activating Token Index: 795

Text #15

Max Range: 1.5080. Min Range: -1.5080

Max Act: 0.6222. Min Act: -0.0000

Data Index: 1367262 (Python Code)

Max Activating Token Index: 61

Text #16

Max Range: 1.5080. Min Range: -1.5080

Max Act: 0.5854. Min Act: -0.0000

Data Index: 1638006 (Python Code)

Max Activating Token Index: 39

Text #17

Max Range: 1.5080. Min Range: -1.5080

Max Act: 0.5943. Min Act: -0.0000

Data Index: 1591075 (Python Code)

Max Activating Token Index: 742

Text #18

Max Range: 1.5080. Min Range: -1.5080

Max Act: 0.5766. Min Act: -0.0000

Data Index: 1470693 (Python Code)

Max Activating Token Index: 426

Text #19

Max Range: 1.5080. Min Range: -1.5080

Max Act: 0.5582. Min Act: -0.0000

Data Index: 1383398 (Python Code)

Max Activating Token Index: 280