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

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

Neuron 4675 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: 1.3728. Min Range: -1.3728

Max Act: 1.3728. Min Act: -0.0000

Data Index: 1493304 (Python Code)

Max Activating Token Index: 987

Text #1

Max Range: 1.3728. Min Range: -1.3728

Max Act: 1.0785. Min Act: -0.0000

Data Index: 1524566 (Python Code)

Max Activating Token Index: 65

Text #2

Max Range: 1.3728. Min Range: -1.3728

Max Act: 0.9276. Min Act: -0.0000

Data Index: 1491589 (Python Code)

Max Activating Token Index: 835

Text #3

Max Range: 1.3728. Min Range: -1.3728

Max Act: 0.9117. Min Act: -0.0000

Data Index: 1417896 (Python Code)

Max Activating Token Index: 1012

Text #4

Max Range: 1.3728. Min Range: -1.3728

Max Act: 0.8839. Min Act: -0.0000

Data Index: 1600993 (Python Code)

Max Activating Token Index: 965

Text #5

Max Range: 1.3728. Min Range: -1.3728

Max Act: 0.7794. Min Act: -0.0000

Data Index: 1494239 (Python Code)

Max Activating Token Index: 129

Text #6

Max Range: 1.3728. Min Range: -1.3728

Max Act: 0.8102. Min Act: -0.0000

Data Index: 1532218 (Python Code)

Max Activating Token Index: 42

Text #7

Max Range: 1.3728. Min Range: -1.3728

Max Act: 0.8040. Min Act: -0.0000

Data Index: 1396308 (Python Code)

Max Activating Token Index: 227

Text #8

Max Range: 1.3728. Min Range: -1.3728

Max Act: 0.8802. Min Act: -0.0000

Data Index: 1388781 (Python Code)

Max Activating Token Index: 224

Text #9

Max Range: 1.3728. Min Range: -1.3728

Max Act: 0.7299. Min Act: -0.0000

Data Index: 1600862 (Python Code)

Max Activating Token Index: 241

Text #10

Max Range: 1.3728. Min Range: -1.3728

Max Act: 0.7257. Min Act: -0.0000

Data Index: 1579421 (Python Code)

Max Activating Token Index: 119

Text #11

Max Range: 1.3728. Min Range: -1.3728

Max Act: 0.7631. Min Act: -0.0000

Data Index: 1621412 (Python Code)

Max Activating Token Index: 621

Text #12

Max Range: 1.3728. Min Range: -1.3728

Max Act: 0.7187. Min Act: -0.0000

Data Index: 1644637 (Python Code)

Max Activating Token Index: 441

Text #13

Max Range: 1.3728. Min Range: -1.3728

Max Act: 0.7533. Min Act: -0.0000

Data Index: 1373371 (Python Code)

Max Activating Token Index: 932

Text #14

Max Range: 1.3728. Min Range: -1.3728

Max Act: 0.7164. Min Act: -0.0000

Data Index: 1484116 (Python Code)

Max Activating Token Index: 35

Text #15

Max Range: 1.3728. Min Range: -1.3728

Max Act: 0.7161. Min Act: -0.0000

Data Index: 1443000 (Python Code)

Max Activating Token Index: 250

Text #16

Max Range: 1.3728. Min Range: -1.3728

Max Act: 0.7081. Min Act: -0.0000

Data Index: 1393463 (Python Code)

Max Activating Token Index: 513

Text #17

Max Range: 1.3728. Min Range: -1.3728

Max Act: 0.6811. Min Act: -0.0000

Data Index: 1473465 (Python Code)

Max Activating Token Index: 204

Text #18

Max Range: 1.3728. Min Range: -1.3728

Max Act: 0.6950. Min Act: -0.0000

Data Index: 1444635 (Python Code)

Max Activating Token Index: 1019

Text #19

Max Range: 1.3728. Min Range: -1.3728

Max Act: 0.6838. Min Act: -0.0000

Data Index: 1654363 (Python Code)

Max Activating Token Index: 725