Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4573 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.1291. Min Range: -1.1291

Max Act: 1.1291. Min Act: -0.0000

Data Index: 1382878 (Python Code)

Max Activating Token Index: 759

Text #1

Max Range: 1.1291. Min Range: -1.1291

Max Act: 0.9190. Min Act: 0.0000

Data Index: 1553124 (Python Code)

Max Activating Token Index: 386

Text #2

Max Range: 1.1291. Min Range: -1.1291

Max Act: 0.8733. Min Act: -0.0000

Data Index: 1586246 (Python Code)

Max Activating Token Index: 725

Text #3

Max Range: 1.1291. Min Range: -1.1291

Max Act: 0.8084. Min Act: -0.0000

Data Index: 1451294 (Python Code)

Max Activating Token Index: 225

Text #4

Max Range: 1.1291. Min Range: -1.1291

Max Act: 0.7619. Min Act: -0.0000

Data Index: 1428594 (Python Code)

Max Activating Token Index: 209

Text #5

Max Range: 1.1291. Min Range: -1.1291

Max Act: 0.7824. Min Act: -0.0000

Data Index: 1510891 (Python Code)

Max Activating Token Index: 768

Text #6

Max Range: 1.1291. Min Range: -1.1291

Max Act: 0.7735. Min Act: 0.0000

Data Index: 1613609 (Python Code)

Max Activating Token Index: 118

Text #7

Max Range: 1.1291. Min Range: -1.1291

Max Act: 0.7413. Min Act: -0.0000

Data Index: 1445711 (Python Code)

Max Activating Token Index: 898

Text #8

Max Range: 1.1291. Min Range: -1.1291

Max Act: 0.7021. Min Act: -0.0000

Data Index: 1409232 (Python Code)

Max Activating Token Index: 404

Text #9

Max Range: 1.1291. Min Range: -1.1291

Max Act: 0.6943. Min Act: 0.0000

Data Index: 1509118 (Python Code)

Max Activating Token Index: 126

Text #10

Max Range: 1.1291. Min Range: -1.1291

Max Act: 0.6738. Min Act: 0.0000

Data Index: 1472063 (Python Code)

Max Activating Token Index: 870

Text #11

Max Range: 1.1291. Min Range: -1.1291

Max Act: 0.6926. Min Act: 0.0000

Data Index: 1479906 (Python Code)

Max Activating Token Index: 406

Text #12

Max Range: 1.1291. Min Range: -1.1291

Max Act: 0.7085. Min Act: -0.0000

Data Index: 1420166 (Python Code)

Max Activating Token Index: 940

Text #13

Max Range: 1.1291. Min Range: -1.1291

Max Act: 0.6420. Min Act: -0.0000

Data Index: 1514068 (Python Code)

Max Activating Token Index: 658

Text #14

Max Range: 1.1291. Min Range: -1.1291

Max Act: 0.6694. Min Act: -0.0000

Data Index: 1565747 (Python Code)

Max Activating Token Index: 219

Text #15

Max Range: 1.1291. Min Range: -1.1291

Max Act: 0.6660. Min Act: -0.0000

Data Index: 1645864 (Python Code)

Max Activating Token Index: 180

Text #16

Max Range: 1.1291. Min Range: -1.1291

Max Act: 0.5811. Min Act: -0.0000

Data Index: 1604677 (Python Code)

Max Activating Token Index: 237

Text #17

Max Range: 1.1291. Min Range: -1.1291

Max Act: 0.6618. Min Act: -0.0000

Data Index: 1531627 (Python Code)

Max Activating Token Index: 744

Text #18

Max Range: 1.1291. Min Range: -1.1291

Max Act: 0.6432. Min Act: -0.0000

Data Index: 1533781 (Python Code)

Max Activating Token Index: 557

Text #19

Max Range: 1.1291. Min Range: -1.1291

Max Act: 0.6127. Min Act: -0.0000

Data Index: 1449502 (Python Code)

Max Activating Token Index: 982