Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 280 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0423. Min Act: -0.0006

Data Index: 1516024 (Python Code)

Max Activating Token Index: 27

Text #1

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0390. Min Act: -0.0006

Data Index: 1599534 (Python Code)

Max Activating Token Index: 768

Text #2

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0347. Min Act: -0.0006

Data Index: 1571154 (Python Code)

Max Activating Token Index: 406

Text #3

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0366. Min Act: -0.0006

Data Index: 1407790 (Python Code)

Max Activating Token Index: 72

Text #4

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0333. Min Act: -0.0006

Data Index: 1559041 (Python Code)

Max Activating Token Index: 30

Text #5

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0347. Min Act: -0.0006

Data Index: 1570181 (Python Code)

Max Activating Token Index: 383

Text #6

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0335. Min Act: -0.0006

Data Index: 1566922 (Python Code)

Max Activating Token Index: 114

Text #7

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0341. Min Act: -0.0006

Data Index: 1475639 (Python Code)

Max Activating Token Index: 225

Text #8

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0349. Min Act: -0.0006

Data Index: 1424207 (Python Code)

Max Activating Token Index: 658

Text #9

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0338. Min Act: -0.0006

Data Index: 1368943 (Python Code)

Max Activating Token Index: 13

Text #10

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0328. Min Act: -0.0006

Data Index: 1518110 (Python Code)

Max Activating Token Index: 149

Text #11

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0328. Min Act: -0.0006

Data Index: 1455601 (Python Code)

Max Activating Token Index: 75

Text #12

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0332. Min Act: -0.0006

Data Index: 1525915 (Python Code)

Max Activating Token Index: 417

Text #13

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0317. Min Act: -0.0006

Data Index: 1613731 (Python Code)

Max Activating Token Index: 466

Text #14

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0330. Min Act: -0.0006

Data Index: 1425939 (Python Code)

Max Activating Token Index: 290

Text #15

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0315. Min Act: -0.0006

Data Index: 1504613 (Python Code)

Max Activating Token Index: 39

Text #16

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0321. Min Act: -0.0006

Data Index: 1640393 (Python Code)

Max Activating Token Index: 357

Text #17

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0319. Min Act: -0.0006

Data Index: 1618474 (Python Code)

Max Activating Token Index: 27

Text #18

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0320. Min Act: -0.0006

Data Index: 1576504 (Python Code)

Max Activating Token Index: 753

Text #19

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0316. Min Act: -0.0006

Data Index: 1599278 (Python Code)

Max Activating Token Index: 292