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

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

Neuron 4837 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1723. Min Range: -0.1723

Max Act: 0.1723. Min Act: -0.0000

Data Index: 1490345 (Python Code)

Max Activating Token Index: 111

Text #1

Max Range: 0.1723. Min Range: -0.1723

Max Act: 0.1498. Min Act: -0.0000

Data Index: 321275 (C4 (Web Text))

Max Activating Token Index: 303

Text #2

Max Range: 0.1723. Min Range: -0.1723

Max Act: 0.1489. Min Act: -0.0000

Data Index: 1539246 (Python Code)

Max Activating Token Index: 929

Text #3

Max Range: 0.1723. Min Range: -0.1723

Max Act: 0.1404. Min Act: -0.0001

Data Index: 1185789 (C4 (Web Text))

Max Activating Token Index: 566

Text #4

Max Range: 0.1723. Min Range: -0.1723

Max Act: 0.1538. Min Act: -0.0000

Data Index: 1485952 (Python Code)

Max Activating Token Index: 339

Text #5

Max Range: 0.1723. Min Range: -0.1723

Max Act: 0.1394. Min Act: -0.0000

Data Index: 1625384 (Python Code)

Max Activating Token Index: 688

Text #6

Max Range: 0.1723. Min Range: -0.1723

Max Act: 0.1297. Min Act: -0.0000

Data Index: 1181391 (C4 (Web Text))

Max Activating Token Index: 464

Text #7

Max Range: 0.1723. Min Range: -0.1723

Max Act: 0.1045. Min Act: -0.0000

Data Index: 205844 (C4 (Web Text))

Max Activating Token Index: 638

Text #8

Max Range: 0.1723. Min Range: -0.1723

Max Act: 0.1285. Min Act: -0.0000

Data Index: 1643691 (Python Code)

Max Activating Token Index: 113

Text #9

Max Range: 0.1723. Min Range: -0.1723

Max Act: 0.1294. Min Act: -0.0001

Data Index: 1068233 (C4 (Web Text))

Max Activating Token Index: 1008

Text #10

Max Range: 0.1723. Min Range: -0.1723

Max Act: 0.1286. Min Act: -0.0000

Data Index: 547576 (C4 (Web Text))

Max Activating Token Index: 787

Text #11

Max Range: 0.1723. Min Range: -0.1723

Max Act: 0.1262. Min Act: -0.0000

Data Index: 1143561 (C4 (Web Text))

Max Activating Token Index: 475

Text #12

Max Range: 0.1723. Min Range: -0.1723

Max Act: 0.1099. Min Act: -0.0001

Data Index: 685462 (C4 (Web Text))

Max Activating Token Index: 869

Text #13

Max Range: 0.1723. Min Range: -0.1723

Max Act: 0.1104. Min Act: -0.0000

Data Index: 1021890 (C4 (Web Text))

Max Activating Token Index: 498

Text #14

Max Range: 0.1723. Min Range: -0.1723

Max Act: 0.1127. Min Act: -0.0000

Data Index: 721122 (C4 (Web Text))

Max Activating Token Index: 894

Text #15

Max Range: 0.1723. Min Range: -0.1723

Max Act: 0.1071. Min Act: -0.0001

Data Index: 896535 (C4 (Web Text))

Max Activating Token Index: 220

Text #16

Max Range: 0.1723. Min Range: -0.1723

Max Act: 0.1071. Min Act: -0.0000

Data Index: 836251 (C4 (Web Text))

Max Activating Token Index: 607

Text #17

Max Range: 0.1723. Min Range: -0.1723

Max Act: 0.1070. Min Act: -0.0000

Data Index: 30059 (C4 (Web Text))

Max Activating Token Index: 539

Text #18

Max Range: 0.1723. Min Range: -0.1723

Max Act: 0.1061. Min Act: -0.0000

Data Index: 190197 (C4 (Web Text))

Max Activating Token Index: 707

Text #19

Max Range: 0.1723. Min Range: -0.1723

Max Act: 0.1104. Min Act: -0.0001

Data Index: 1592008 (Python Code)

Max Activating Token Index: 491