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

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

Neuron 70 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1615. Min Range: -0.1615

Max Act: 0.1615. Min Act: -0.0002

Data Index: 1652267 (Python Code)

Max Activating Token Index: 102

Text #1

Max Range: 0.1615. Min Range: -0.1615

Max Act: 0.1502. Min Act: -0.0002

Data Index: 1496614 (Python Code)

Max Activating Token Index: 112

Text #2

Max Range: 0.1615. Min Range: -0.1615

Max Act: 0.1318. Min Act: -0.0002

Data Index: 1484859 (Python Code)

Max Activating Token Index: 840

Text #3

Max Range: 0.1615. Min Range: -0.1615

Max Act: 0.1509. Min Act: -0.0002

Data Index: 1517295 (Python Code)

Max Activating Token Index: 735

Text #4

Max Range: 0.1615. Min Range: -0.1615

Max Act: 0.1251. Min Act: -0.0002

Data Index: 1400961 (Python Code)

Max Activating Token Index: 754

Text #5

Max Range: 0.1615. Min Range: -0.1615

Max Act: 0.1333. Min Act: -0.0002

Data Index: 1547368 (Python Code)

Max Activating Token Index: 122

Text #6

Max Range: 0.1615. Min Range: -0.1615

Max Act: 0.1438. Min Act: -0.0002

Data Index: 1465638 (Python Code)

Max Activating Token Index: 158

Text #7

Max Range: 0.1615. Min Range: -0.1615

Max Act: 0.1368. Min Act: -0.0002

Data Index: 1564225 (Python Code)

Max Activating Token Index: 163

Text #8

Max Range: 0.1615. Min Range: -0.1615

Max Act: 0.1223. Min Act: -0.0002

Data Index: 1406232 (Python Code)

Max Activating Token Index: 81

Text #9

Max Range: 0.1615. Min Range: -0.1615

Max Act: 0.1335. Min Act: -0.0002

Data Index: 1493856 (Python Code)

Max Activating Token Index: 302

Text #10

Max Range: 0.1615. Min Range: -0.1615

Max Act: 0.1277. Min Act: -0.0002

Data Index: 1378663 (Python Code)

Max Activating Token Index: 52

Text #11

Max Range: 0.1615. Min Range: -0.1615

Max Act: 0.1227. Min Act: -0.0002

Data Index: 1537506 (Python Code)

Max Activating Token Index: 596

Text #12

Max Range: 0.1615. Min Range: -0.1615

Max Act: 0.1246. Min Act: -0.0002

Data Index: 1499829 (Python Code)

Max Activating Token Index: 177

Text #13

Max Range: 0.1615. Min Range: -0.1615

Max Act: 0.1272. Min Act: -0.0002

Data Index: 1487265 (Python Code)

Max Activating Token Index: 294

Text #14

Max Range: 0.1615. Min Range: -0.1615

Max Act: 0.1261. Min Act: -0.0002

Data Index: 1645180 (Python Code)

Max Activating Token Index: 79

Text #15

Max Range: 0.1615. Min Range: -0.1615

Max Act: 0.1254. Min Act: -0.0002

Data Index: 1395956 (Python Code)

Max Activating Token Index: 30

Text #16

Max Range: 0.1615. Min Range: -0.1615

Max Act: 0.1155. Min Act: -0.0002

Data Index: 1506097 (Python Code)

Max Activating Token Index: 61

Text #17

Max Range: 0.1615. Min Range: -0.1615

Max Act: 0.1268. Min Act: -0.0002

Data Index: 1473125 (Python Code)

Max Activating Token Index: 597

Text #18

Max Range: 0.1615. Min Range: -0.1615

Max Act: 0.1229. Min Act: -0.0002

Data Index: 1365053 (Python Code)

Max Activating Token Index: 216

Text #19

Max Range: 0.1615. Min Range: -0.1615

Max Act: 0.1257. Min Act: -0.0002

Data Index: 1576608 (Python Code)

Max Activating Token Index: 829