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

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

Neuron 3237 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8550. Min Range: -3.8550

Max Act: 3.8550. Min Act: -0.0000

Data Index: 1641273 (Python Code)

Max Activating Token Index: 1001

Text #1

Max Range: 3.8550. Min Range: -3.8550

Max Act: 3.3070. Min Act: -0.0000

Data Index: 1645519 (Python Code)

Max Activating Token Index: 470

Text #2

Max Range: 3.8550. Min Range: -3.8550

Max Act: 3.2701. Min Act: -0.0000

Data Index: 1424455 (Python Code)

Max Activating Token Index: 997

Text #3

Max Range: 3.8550. Min Range: -3.8550

Max Act: 3.2639. Min Act: -0.0000

Data Index: 1552339 (Python Code)

Max Activating Token Index: 546

Text #4

Max Range: 3.8550. Min Range: -3.8550

Max Act: 3.2098. Min Act: -0.0000

Data Index: 1589922 (Python Code)

Max Activating Token Index: 575

Text #5

Max Range: 3.8550. Min Range: -3.8550

Max Act: 3.1552. Min Act: -0.0000

Data Index: 1433602 (Python Code)

Max Activating Token Index: 661

Text #6

Max Range: 3.8550. Min Range: -3.8550

Max Act: 3.0153. Min Act: -0.0000

Data Index: 1489820 (Python Code)

Max Activating Token Index: 994

Text #7

Max Range: 3.8550. Min Range: -3.8550

Max Act: 3.3142. Min Act: -0.0000

Data Index: 1477493 (Python Code)

Max Activating Token Index: 1019

Text #8

Max Range: 3.8550. Min Range: -3.8550

Max Act: 2.9624. Min Act: -0.0000

Data Index: 1559523 (Python Code)

Max Activating Token Index: 930

Text #9

Max Range: 3.8550. Min Range: -3.8550

Max Act: 3.1054. Min Act: -0.0000

Data Index: 1566143 (Python Code)

Max Activating Token Index: 510

Text #10

Max Range: 3.8550. Min Range: -3.8550

Max Act: 2.9331. Min Act: -0.0000

Data Index: 1613908 (Python Code)

Max Activating Token Index: 88

Text #11

Max Range: 3.8550. Min Range: -3.8550

Max Act: 2.9058. Min Act: -0.0000

Data Index: 1562266 (Python Code)

Max Activating Token Index: 649

Text #12

Max Range: 3.8550. Min Range: -3.8550

Max Act: 3.0401. Min Act: -0.0000

Data Index: 1470129 (Python Code)

Max Activating Token Index: 682

Text #13

Max Range: 3.8550. Min Range: -3.8550

Max Act: 2.6805. Min Act: -0.0000

Data Index: 1553073 (Python Code)

Max Activating Token Index: 256

Text #14

Max Range: 3.8550. Min Range: -3.8550

Max Act: 2.7307. Min Act: -0.0000

Data Index: 1399280 (Python Code)

Max Activating Token Index: 992

Text #15

Max Range: 3.8550. Min Range: -3.8550

Max Act: 2.8396. Min Act: -0.0000

Data Index: 1569765 (Python Code)

Max Activating Token Index: 995

Text #16

Max Range: 3.8550. Min Range: -3.8550

Max Act: 2.8203. Min Act: -0.0000

Data Index: 1551477 (Python Code)

Max Activating Token Index: 662

Text #17

Max Range: 3.8550. Min Range: -3.8550

Max Act: 2.8287. Min Act: -0.0000

Data Index: 1584970 (Python Code)

Max Activating Token Index: 202

Text #18

Max Range: 3.8550. Min Range: -3.8550

Max Act: 2.7792. Min Act: -0.0000

Data Index: 1535273 (Python Code)

Max Activating Token Index: 402

Text #19

Max Range: 3.8550. Min Range: -3.8550

Max Act: 2.6961. Min Act: -0.0000

Data Index: 1446711 (Python Code)

Max Activating Token Index: 731