Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 187 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.9718. Min Range: -0.9718

Max Act: 0.9253. Min Act: -0.0001

Data Index: 1626989 (Python Code)

Max Activating Token Index: 14

Text #1

Max Range: 0.9718. Min Range: -0.9718

Max Act: 0.9718. Min Act: -0.0001

Data Index: 1444511 (Python Code)

Max Activating Token Index: 76

Text #2

Max Range: 0.9718. Min Range: -0.9718

Max Act: 0.7921. Min Act: -0.0001

Data Index: 1573501 (Python Code)

Max Activating Token Index: 644

Text #3

Max Range: 0.9718. Min Range: -0.9718

Max Act: 0.8154. Min Act: -0.0001

Data Index: 1603703 (Python Code)

Max Activating Token Index: 670

Text #4

Max Range: 0.9718. Min Range: -0.9718

Max Act: 0.8260. Min Act: -0.0001

Data Index: 1433532 (Python Code)

Max Activating Token Index: 463

Text #5

Max Range: 0.9718. Min Range: -0.9718

Max Act: 0.8455. Min Act: -0.0001

Data Index: 1509343 (Python Code)

Max Activating Token Index: 197

Text #6

Max Range: 0.9718. Min Range: -0.9718

Max Act: 0.7864. Min Act: -0.0001

Data Index: 1426976 (Python Code)

Max Activating Token Index: 102

Text #7

Max Range: 0.9718. Min Range: -0.9718

Max Act: 0.7134. Min Act: -0.0001

Data Index: 1492718 (Python Code)

Max Activating Token Index: 81

Text #8

Max Range: 0.9718. Min Range: -0.9718

Max Act: 0.7746. Min Act: -0.0001

Data Index: 1424886 (Python Code)

Max Activating Token Index: 850

Text #9

Max Range: 0.9718. Min Range: -0.9718

Max Act: 0.7151. Min Act: -0.0001

Data Index: 1550112 (Python Code)

Max Activating Token Index: 547

Text #10

Max Range: 0.9718. Min Range: -0.9718

Max Act: 0.6444. Min Act: -0.0001

Data Index: 1651363 (Python Code)

Max Activating Token Index: 772

Text #11

Max Range: 0.9718. Min Range: -0.9718

Max Act: 0.6892. Min Act: -0.0001

Data Index: 1366469 (Python Code)

Max Activating Token Index: 252

Text #12

Max Range: 0.9718. Min Range: -0.9718

Max Act: 0.6922. Min Act: -0.0001

Data Index: 1635128 (Python Code)

Max Activating Token Index: 903

Text #13

Max Range: 0.9718. Min Range: -0.9718

Max Act: 0.7610. Min Act: -0.0001

Data Index: 1605787 (Python Code)

Max Activating Token Index: 53

Text #14

Max Range: 0.9718. Min Range: -0.9718

Max Act: 0.6050. Min Act: -0.0001

Data Index: 1481138 (Python Code)

Max Activating Token Index: 11

Text #15

Max Range: 0.9718. Min Range: -0.9718

Max Act: 0.6873. Min Act: -0.0001

Data Index: 1371008 (Python Code)

Max Activating Token Index: 287

Text #16

Max Range: 0.9718. Min Range: -0.9718

Max Act: 0.7107. Min Act: -0.0001

Data Index: 1643462 (Python Code)

Max Activating Token Index: 164

Text #17

Max Range: 0.9718. Min Range: -0.9718

Max Act: 0.6840. Min Act: -0.0001

Data Index: 1504263 (Python Code)

Max Activating Token Index: 401

Text #18

Max Range: 0.9718. Min Range: -0.9718

Max Act: 0.6641. Min Act: -0.0001

Data Index: 1375739 (Python Code)

Max Activating Token Index: 872

Text #19

Max Range: 0.9718. Min Range: -0.9718

Max Act: 0.6345. Min Act: -0.0001

Data Index: 1626753 (Python Code)

Max Activating Token Index: 620