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

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

Neuron 821 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: 0.1404. Min Range: -0.1404

Max Act: 0.1404. Min Act: -0.0001

Data Index: 952070 (C4 (Web Text))

Max Activating Token Index: 781

Text #1

Max Range: 0.1404. Min Range: -0.1404

Max Act: 0.1124. Min Act: -0.0001

Data Index: 274485 (C4 (Web Text))

Max Activating Token Index: 321

Text #2

Max Range: 0.1404. Min Range: -0.1404

Max Act: 0.1039. Min Act: -0.0001

Data Index: 1447160 (Python Code)

Max Activating Token Index: 103

Text #3

Max Range: 0.1404. Min Range: -0.1404

Max Act: 0.1043. Min Act: -0.0001

Data Index: 1362750 (Python Code)

Max Activating Token Index: 28

Text #4

Max Range: 0.1404. Min Range: -0.1404

Max Act: 0.0977. Min Act: -0.0001

Data Index: 1444160 (Python Code)

Max Activating Token Index: 40

Text #5

Max Range: 0.1404. Min Range: -0.1404

Max Act: 0.0862. Min Act: -0.0001

Data Index: 1388775 (Python Code)

Max Activating Token Index: 821

Text #6

Max Range: 0.1404. Min Range: -0.1404

Max Act: 0.0893. Min Act: -0.0001

Data Index: 1392599 (Python Code)

Max Activating Token Index: 175

Text #7

Max Range: 0.1404. Min Range: -0.1404

Max Act: 0.0951. Min Act: -0.0001

Data Index: 954394 (C4 (Web Text))

Max Activating Token Index: 838

Text #8

Max Range: 0.1404. Min Range: -0.1404

Max Act: 0.0920. Min Act: -0.0001

Data Index: 1516269 (Python Code)

Max Activating Token Index: 924

Text #9

Max Range: 0.1404. Min Range: -0.1404

Max Act: 0.0956. Min Act: -0.0001

Data Index: 1441853 (Python Code)

Max Activating Token Index: 669

Text #10

Max Range: 0.1404. Min Range: -0.1404

Max Act: 0.0988. Min Act: -0.0001

Data Index: 1487162 (Python Code)

Max Activating Token Index: 396

Text #11

Max Range: 0.1404. Min Range: -0.1404

Max Act: 0.0880. Min Act: -0.0001

Data Index: 1428732 (Python Code)

Max Activating Token Index: 466

Text #12

Max Range: 0.1404. Min Range: -0.1404

Max Act: 0.0911. Min Act: -0.0001

Data Index: 1620494 (Python Code)

Max Activating Token Index: 512

Text #13

Max Range: 0.1404. Min Range: -0.1404

Max Act: 0.0875. Min Act: -0.0001

Data Index: 1600256 (Python Code)

Max Activating Token Index: 77

Text #14

Max Range: 0.1404. Min Range: -0.1404

Max Act: 0.0974. Min Act: -0.0001

Data Index: 1562088 (Python Code)

Max Activating Token Index: 779

Text #15

Max Range: 0.1404. Min Range: -0.1404

Max Act: 0.0890. Min Act: -0.0001

Data Index: 1173979 (C4 (Web Text))

Max Activating Token Index: 507

Text #16

Max Range: 0.1404. Min Range: -0.1404

Max Act: 0.0860. Min Act: -0.0001

Data Index: 1526715 (Python Code)

Max Activating Token Index: 218

Text #17

Max Range: 0.1404. Min Range: -0.1404

Max Act: 0.0994. Min Act: -0.0001

Data Index: 1394452 (Python Code)

Max Activating Token Index: 229

Text #18

Max Range: 0.1404. Min Range: -0.1404

Max Act: 0.0849. Min Act: -0.0001

Data Index: 1541945 (Python Code)

Max Activating Token Index: 660

Text #19

Max Range: 0.1404. Min Range: -0.1404

Max Act: 0.0838. Min Act: -0.0001

Data Index: 1649612 (Python Code)

Max Activating Token Index: 833