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

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

Neuron 1064 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0540. Min Range: -1.0540

Max Act: 1.0540. Min Act: -0.0001

Data Index: 1512559 (Python Code)

Max Activating Token Index: 533

Text #1

Max Range: 1.0540. Min Range: -1.0540

Max Act: 0.9216. Min Act: -0.0001

Data Index: 1376173 (Python Code)

Max Activating Token Index: 616

Text #2

Max Range: 1.0540. Min Range: -1.0540

Max Act: 0.8283. Min Act: -0.0001

Data Index: 1442032 (Python Code)

Max Activating Token Index: 350

Text #3

Max Range: 1.0540. Min Range: -1.0540

Max Act: 0.7624. Min Act: -0.0001

Data Index: 1395671 (Python Code)

Max Activating Token Index: 689

Text #4

Max Range: 1.0540. Min Range: -1.0540

Max Act: 0.8657. Min Act: -0.0001

Data Index: 1557621 (Python Code)

Max Activating Token Index: 56

Text #5

Max Range: 1.0540. Min Range: -1.0540

Max Act: 0.7518. Min Act: -0.0001

Data Index: 1427066 (Python Code)

Max Activating Token Index: 873

Text #6

Max Range: 1.0540. Min Range: -1.0540

Max Act: 0.7010. Min Act: -0.0001

Data Index: 1369088 (Python Code)

Max Activating Token Index: 304

Text #7

Max Range: 1.0540. Min Range: -1.0540

Max Act: 0.7202. Min Act: -0.0001

Data Index: 1656295 (Python Code)

Max Activating Token Index: 7

Text #8

Max Range: 1.0540. Min Range: -1.0540

Max Act: 0.7269. Min Act: -0.0001

Data Index: 1595116 (Python Code)

Max Activating Token Index: 879

Text #9

Max Range: 1.0540. Min Range: -1.0540

Max Act: 0.7286. Min Act: -0.0001

Data Index: 1610806 (Python Code)

Max Activating Token Index: 288

Text #10

Max Range: 1.0540. Min Range: -1.0540

Max Act: 0.7107. Min Act: -0.0001

Data Index: 1562164 (Python Code)

Max Activating Token Index: 739

Text #11

Max Range: 1.0540. Min Range: -1.0540

Max Act: 0.7362. Min Act: -0.0001

Data Index: 1384007 (Python Code)

Max Activating Token Index: 256

Text #12

Max Range: 1.0540. Min Range: -1.0540

Max Act: 0.7296. Min Act: -0.0001

Data Index: 1539711 (Python Code)

Max Activating Token Index: 168

Text #13

Max Range: 1.0540. Min Range: -1.0540

Max Act: 0.7820. Min Act: -0.0001

Data Index: 1375110 (Python Code)

Max Activating Token Index: 876

Text #14

Max Range: 1.0540. Min Range: -1.0540

Max Act: 0.7316. Min Act: -0.0001

Data Index: 1635794 (Python Code)

Max Activating Token Index: 794

Text #15

Max Range: 1.0540. Min Range: -1.0540

Max Act: 0.6453. Min Act: -0.0001

Data Index: 1565948 (Python Code)

Max Activating Token Index: 813

Text #16

Max Range: 1.0540. Min Range: -1.0540

Max Act: 0.6579. Min Act: -0.0001

Data Index: 1596283 (Python Code)

Max Activating Token Index: 696

Text #17

Max Range: 1.0540. Min Range: -1.0540

Max Act: 0.6815. Min Act: -0.0001

Data Index: 1488838 (Python Code)

Max Activating Token Index: 751

Text #18

Max Range: 1.0540. Min Range: -1.0540

Max Act: 0.7018. Min Act: -0.0001

Data Index: 1549270 (Python Code)

Max Activating Token Index: 765

Text #19

Max Range: 1.0540. Min Range: -1.0540

Max Act: 0.6303. Min Act: -0.0001

Data Index: 1491471 (Python Code)

Max Activating Token Index: 751