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

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

Neuron 1653 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7651. Min Range: -0.7651

Max Act: 0.7651. Min Act: -0.0000

Data Index: 1246306 (C4 (Web Text))

Max Activating Token Index: 300

Text #1

Max Range: 0.7651. Min Range: -0.7651

Max Act: 0.5999. Min Act: -0.0000

Data Index: 115924 (C4 (Web Text))

Max Activating Token Index: 67

Text #2

Max Range: 0.7651. Min Range: -0.7651

Max Act: 0.5110. Min Act: -0.0000

Data Index: 1398638 (Python Code)

Max Activating Token Index: 342

Text #3

Max Range: 0.7651. Min Range: -0.7651

Max Act: 0.4227. Min Act: -0.0000

Data Index: 1370428 (Python Code)

Max Activating Token Index: 484

Text #4

Max Range: 0.7651. Min Range: -0.7651

Max Act: 0.4526. Min Act: -0.0000

Data Index: 1636068 (Python Code)

Max Activating Token Index: 641

Text #5

Max Range: 0.7651. Min Range: -0.7651

Max Act: 0.4230. Min Act: -0.0000

Data Index: 158470 (C4 (Web Text))

Max Activating Token Index: 783

Text #6

Max Range: 0.7651. Min Range: -0.7651

Max Act: 0.3776. Min Act: 0.0000

Data Index: 1400430 (Python Code)

Max Activating Token Index: 880

Text #7

Max Range: 0.7651. Min Range: -0.7651

Max Act: 0.3947. Min Act: -0.0000

Data Index: 1449029 (Python Code)

Max Activating Token Index: 658

Text #8

Max Range: 0.7651. Min Range: -0.7651

Max Act: 0.3687. Min Act: 0.0001

Data Index: 1447482 (Python Code)

Max Activating Token Index: 680

Text #9

Max Range: 0.7651. Min Range: -0.7651

Max Act: 0.3630. Min Act: -0.0000

Data Index: 1504060 (Python Code)

Max Activating Token Index: 85

Text #10

Max Range: 0.7651. Min Range: -0.7651

Max Act: 0.3704. Min Act: 0.0001

Data Index: 1444320 (Python Code)

Max Activating Token Index: 686

Text #11

Max Range: 0.7651. Min Range: -0.7651

Max Act: 0.3438. Min Act: -0.0000

Data Index: 1585850 (Python Code)

Max Activating Token Index: 681

Text #12

Max Range: 0.7651. Min Range: -0.7651

Max Act: 0.3626. Min Act: -0.0000

Data Index: 1633470 (Python Code)

Max Activating Token Index: 20

Text #13

Max Range: 0.7651. Min Range: -0.7651

Max Act: 0.2705. Min Act: -0.0000

Data Index: 1132656 (C4 (Web Text))

Max Activating Token Index: 867

Text #14

Max Range: 0.7651. Min Range: -0.7651

Max Act: 0.3377. Min Act: -0.0000

Data Index: 1507434 (Python Code)

Max Activating Token Index: 30

Text #15

Max Range: 0.7651. Min Range: -0.7651

Max Act: 0.3186. Min Act: 0.0000

Data Index: 1418334 (Python Code)

Max Activating Token Index: 984

Text #16

Max Range: 0.7651. Min Range: -0.7651

Max Act: 0.3089. Min Act: -0.0000

Data Index: 1616761 (Python Code)

Max Activating Token Index: 844

Text #17

Max Range: 0.7651. Min Range: -0.7651

Max Act: 0.3187. Min Act: 0.0000

Data Index: 1481444 (Python Code)

Max Activating Token Index: 774

Text #18

Max Range: 0.7651. Min Range: -0.7651

Max Act: 0.2933. Min Act: -0.0000

Data Index: 1377217 (Python Code)

Max Activating Token Index: 311

Text #19

Max Range: 0.7651. Min Range: -0.7651

Max Act: 0.3105. Min Act: -0.0000

Data Index: 1616109 (Python Code)

Max Activating Token Index: 15