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

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

Neuron 557 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.4758. Min Range: -5.4758

Max Act: 5.4758. Min Act: -0.0001

Data Index: 1631261 (Python Code)

Max Activating Token Index: 586

Text #1

Max Range: 5.4758. Min Range: -5.4758

Max Act: 3.9626. Min Act: -0.0001

Data Index: 1534654 (Python Code)

Max Activating Token Index: 830

Text #2

Max Range: 5.4758. Min Range: -5.4758

Max Act: 4.3539. Min Act: -0.0000

Data Index: 1632928 (Python Code)

Max Activating Token Index: 350

Text #3

Max Range: 5.4758. Min Range: -5.4758

Max Act: 4.4094. Min Act: -0.0000

Data Index: 1644099 (Python Code)

Max Activating Token Index: 500

Text #4

Max Range: 5.4758. Min Range: -5.4758

Max Act: 4.2265. Min Act: -0.0000

Data Index: 1606517 (Python Code)

Max Activating Token Index: 210

Text #5

Max Range: 5.4758. Min Range: -5.4758

Max Act: 3.9168. Min Act: -0.0000

Data Index: 1463488 (Python Code)

Max Activating Token Index: 993

Text #6

Max Range: 5.4758. Min Range: -5.4758

Max Act: 3.9176. Min Act: -0.0001

Data Index: 1590112 (Python Code)

Max Activating Token Index: 1012

Text #7

Max Range: 5.4758. Min Range: -5.4758

Max Act: 3.7616. Min Act: -0.0000

Data Index: 1469478 (Python Code)

Max Activating Token Index: 866

Text #8

Max Range: 5.4758. Min Range: -5.4758

Max Act: 4.0636. Min Act: -0.0000

Data Index: 1465004 (Python Code)

Max Activating Token Index: 207

Text #9

Max Range: 5.4758. Min Range: -5.4758

Max Act: 3.7586. Min Act: -0.0000

Data Index: 1531984 (Python Code)

Max Activating Token Index: 221

Text #10

Max Range: 5.4758. Min Range: -5.4758

Max Act: 3.8991. Min Act: -0.0000

Data Index: 1389474 (Python Code)

Max Activating Token Index: 970

Text #11

Max Range: 5.4758. Min Range: -5.4758

Max Act: 4.0591. Min Act: -0.0000

Data Index: 1381307 (Python Code)

Max Activating Token Index: 189

Text #12

Max Range: 5.4758. Min Range: -5.4758

Max Act: 4.0109. Min Act: -0.0000

Data Index: 1523484 (Python Code)

Max Activating Token Index: 319

Text #13

Max Range: 5.4758. Min Range: -5.4758

Max Act: 3.9603. Min Act: -0.0000

Data Index: 1627986 (Python Code)

Max Activating Token Index: 235

Text #14

Max Range: 5.4758. Min Range: -5.4758

Max Act: 3.7573. Min Act: -0.0000

Data Index: 1607554 (Python Code)

Max Activating Token Index: 114

Text #15

Max Range: 5.4758. Min Range: -5.4758

Max Act: 4.2058. Min Act: -0.0000

Data Index: 1494633 (Python Code)

Max Activating Token Index: 165

Text #16

Max Range: 5.4758. Min Range: -5.4758

Max Act: 3.4162. Min Act: -0.0001

Data Index: 1553736 (Python Code)

Max Activating Token Index: 396

Text #17

Max Range: 5.4758. Min Range: -5.4758

Max Act: 3.7077. Min Act: -0.0000

Data Index: 1430810 (Python Code)

Max Activating Token Index: 89

Text #18

Max Range: 5.4758. Min Range: -5.4758

Max Act: 3.4988. Min Act: -0.0001

Data Index: 1586236 (Python Code)

Max Activating Token Index: 82

Text #19

Max Range: 5.4758. Min Range: -5.4758

Max Act: 3.6430. Min Act: -0.0000

Data Index: 1398083 (Python Code)

Max Activating Token Index: 681