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

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

Neuron 1078 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 1.7134. Min Range: -1.7134

Max Act: 1.7134. Min Act: -0.0002

Data Index: 1410505 (Python Code)

Max Activating Token Index: 895

Text #1

Max Range: 1.7134. Min Range: -1.7134

Max Act: 1.6615. Min Act: -0.0002

Data Index: 1427409 (Python Code)

Max Activating Token Index: 188

Text #2

Max Range: 1.7134. Min Range: -1.7134

Max Act: 1.6775. Min Act: -0.0002

Data Index: 1623271 (Python Code)

Max Activating Token Index: 118

Text #3

Max Range: 1.7134. Min Range: -1.7134

Max Act: 1.5951. Min Act: -0.0002

Data Index: 1383463 (Python Code)

Max Activating Token Index: 10

Text #4

Max Range: 1.7134. Min Range: -1.7134

Max Act: 1.5788. Min Act: -0.0002

Data Index: 1446236 (Python Code)

Max Activating Token Index: 887

Text #5

Max Range: 1.7134. Min Range: -1.7134

Max Act: 1.5362. Min Act: -0.0002

Data Index: 1414544 (Python Code)

Max Activating Token Index: 5

Text #6

Max Range: 1.7134. Min Range: -1.7134

Max Act: 1.4949. Min Act: -0.0002

Data Index: 1643325 (Python Code)

Max Activating Token Index: 62

Text #7

Max Range: 1.7134. Min Range: -1.7134

Max Act: 1.4592. Min Act: -0.0002

Data Index: 1433913 (Python Code)

Max Activating Token Index: 403

Text #8

Max Range: 1.7134. Min Range: -1.7134

Max Act: 1.4902. Min Act: -0.0002

Data Index: 1461227 (Python Code)

Max Activating Token Index: 460

Text #9

Max Range: 1.7134. Min Range: -1.7134

Max Act: 1.4845. Min Act: -0.0002

Data Index: 1444528 (Python Code)

Max Activating Token Index: 12

Text #10

Max Range: 1.7134. Min Range: -1.7134

Max Act: 1.4724. Min Act: -0.0002

Data Index: 1457550 (Python Code)

Max Activating Token Index: 109

Text #11

Max Range: 1.7134. Min Range: -1.7134

Max Act: 1.4513. Min Act: -0.0002

Data Index: 1564122 (Python Code)

Max Activating Token Index: 739

Text #12

Max Range: 1.7134. Min Range: -1.7134

Max Act: 1.5063. Min Act: -0.0002

Data Index: 1444508 (Python Code)

Max Activating Token Index: 52

Text #13

Max Range: 1.7134. Min Range: -1.7134

Max Act: 1.4375. Min Act: -0.0002

Data Index: 1592065 (Python Code)

Max Activating Token Index: 247

Text #14

Max Range: 1.7134. Min Range: -1.7134

Max Act: 1.4013. Min Act: -0.0002

Data Index: 1365120 (Python Code)

Max Activating Token Index: 842

Text #15

Max Range: 1.7134. Min Range: -1.7134

Max Act: 1.4088. Min Act: -0.0002

Data Index: 1549370 (Python Code)

Max Activating Token Index: 673

Text #16

Max Range: 1.7134. Min Range: -1.7134

Max Act: 1.4199. Min Act: -0.0002

Data Index: 1583172 (Python Code)

Max Activating Token Index: 426

Text #17

Max Range: 1.7134. Min Range: -1.7134

Max Act: 1.3895. Min Act: -0.0002

Data Index: 1475358 (Python Code)

Max Activating Token Index: 24

Text #18

Max Range: 1.7134. Min Range: -1.7134

Max Act: 1.3861. Min Act: -0.0002

Data Index: 1505581 (Python Code)

Max Activating Token Index: 527

Text #19

Max Range: 1.7134. Min Range: -1.7134

Max Act: 1.3622. Min Act: -0.0002

Data Index: 1447778 (Python Code)

Max Activating Token Index: 856