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

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

Neuron 1863 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4659. Min Range: -0.4659

Max Act: 0.4517. Min Act: -0.0001

Data Index: 1596853 (Python Code)

Max Activating Token Index: 46

Text #1

Max Range: 0.4659. Min Range: -0.4659

Max Act: 0.4659. Min Act: -0.0001

Data Index: 1630811 (Python Code)

Max Activating Token Index: 707

Text #2

Max Range: 0.4659. Min Range: -0.4659

Max Act: 0.4135. Min Act: -0.0001

Data Index: 1623868 (Python Code)

Max Activating Token Index: 983

Text #3

Max Range: 0.4659. Min Range: -0.4659

Max Act: 0.4143. Min Act: -0.0001

Data Index: 607226 (C4 (Web Text))

Max Activating Token Index: 113

Text #4

Max Range: 0.4659. Min Range: -0.4659

Max Act: 0.4428. Min Act: -0.0001

Data Index: 1557896 (Python Code)

Max Activating Token Index: 670

Text #5

Max Range: 0.4659. Min Range: -0.4659

Max Act: 0.4165. Min Act: -0.0001

Data Index: 846525 (C4 (Web Text))

Max Activating Token Index: 214

Text #6

Max Range: 0.4659. Min Range: -0.4659

Max Act: 0.4009. Min Act: -0.0001

Data Index: 1567254 (Python Code)

Max Activating Token Index: 224

Text #7

Max Range: 0.4659. Min Range: -0.4659

Max Act: 0.4410. Min Act: -0.0001

Data Index: 1442663 (Python Code)

Max Activating Token Index: 725

Text #8

Max Range: 0.4659. Min Range: -0.4659

Max Act: 0.4101. Min Act: -0.0001

Data Index: 1596036 (Python Code)

Max Activating Token Index: 780

Text #9

Max Range: 0.4659. Min Range: -0.4659

Max Act: 0.3785. Min Act: -0.0001

Data Index: 59163 (C4 (Web Text))

Max Activating Token Index: 809

Text #10

Max Range: 0.4659. Min Range: -0.4659

Max Act: 0.4322. Min Act: -0.0001

Data Index: 298186 (C4 (Web Text))

Max Activating Token Index: 154

Text #11

Max Range: 0.4659. Min Range: -0.4659

Max Act: 0.3918. Min Act: -0.0001

Data Index: 657056 (C4 (Web Text))

Max Activating Token Index: 73

Text #12

Max Range: 0.4659. Min Range: -0.4659

Max Act: 0.3632. Min Act: -0.0001

Data Index: 1502563 (Python Code)

Max Activating Token Index: 943

Text #13

Max Range: 0.4659. Min Range: -0.4659

Max Act: 0.3761. Min Act: -0.0001

Data Index: 1503254 (Python Code)

Max Activating Token Index: 954

Text #14

Max Range: 0.4659. Min Range: -0.4659

Max Act: 0.3636. Min Act: -0.0001

Data Index: 1420267 (Python Code)

Max Activating Token Index: 393

Text #15

Max Range: 0.4659. Min Range: -0.4659

Max Act: 0.3476. Min Act: -0.0001

Data Index: 1091461 (C4 (Web Text))

Max Activating Token Index: 192

Text #16

Max Range: 0.4659. Min Range: -0.4659

Max Act: 0.4112. Min Act: -0.0001

Data Index: 1588304 (Python Code)

Max Activating Token Index: 559

Text #17

Max Range: 0.4659. Min Range: -0.4659

Max Act: 0.3771. Min Act: -0.0001

Data Index: 1466652 (Python Code)

Max Activating Token Index: 904

Text #18

Max Range: 0.4659. Min Range: -0.4659

Max Act: 0.3459. Min Act: -0.0001

Data Index: 1623318 (Python Code)

Max Activating Token Index: 209

Text #19

Max Range: 0.4659. Min Range: -0.4659

Max Act: 0.4166. Min Act: -0.0001

Data Index: 1610129 (Python Code)

Max Activating Token Index: 925