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

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

Neuron 931 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: 0.7142. Min Range: -0.7142

Max Act: 0.7142. Min Act: -0.0000

Data Index: 1430548 (Python Code)

Max Activating Token Index: 639

Text #1

Max Range: 0.7142. Min Range: -0.7142

Max Act: 0.7052. Min Act: -0.0000

Data Index: 1460651 (Python Code)

Max Activating Token Index: 941

Text #2

Max Range: 0.7142. Min Range: -0.7142

Max Act: 0.7000. Min Act: -0.0000

Data Index: 1480442 (Python Code)

Max Activating Token Index: 871

Text #3

Max Range: 0.7142. Min Range: -0.7142

Max Act: 0.6769. Min Act: -0.0000

Data Index: 1647069 (Python Code)

Max Activating Token Index: 395

Text #4

Max Range: 0.7142. Min Range: -0.7142

Max Act: 0.6565. Min Act: -0.0000

Data Index: 1642246 (Python Code)

Max Activating Token Index: 187

Text #5

Max Range: 0.7142. Min Range: -0.7142

Max Act: 0.6549. Min Act: -0.0000

Data Index: 1497400 (Python Code)

Max Activating Token Index: 886

Text #6

Max Range: 0.7142. Min Range: -0.7142

Max Act: 0.6450. Min Act: -0.0000

Data Index: 1522560 (Python Code)

Max Activating Token Index: 108

Text #7

Max Range: 0.7142. Min Range: -0.7142

Max Act: 0.6356. Min Act: -0.0000

Data Index: 1613542 (Python Code)

Max Activating Token Index: 596

Text #8

Max Range: 0.7142. Min Range: -0.7142

Max Act: 0.6237. Min Act: -0.0000

Data Index: 1440051 (Python Code)

Max Activating Token Index: 123

Text #9

Max Range: 0.7142. Min Range: -0.7142

Max Act: 0.6329. Min Act: -0.0000

Data Index: 1424266 (Python Code)

Max Activating Token Index: 473

Text #10

Max Range: 0.7142. Min Range: -0.7142

Max Act: 0.5938. Min Act: -0.0000

Data Index: 1569714 (Python Code)

Max Activating Token Index: 203

Text #11

Max Range: 0.7142. Min Range: -0.7142

Max Act: 0.5737. Min Act: -0.0000

Data Index: 1478669 (Python Code)

Max Activating Token Index: 291

Text #12

Max Range: 0.7142. Min Range: -0.7142

Max Act: 0.5949. Min Act: -0.0000

Data Index: 1559114 (Python Code)

Max Activating Token Index: 48

Text #13

Max Range: 0.7142. Min Range: -0.7142

Max Act: 0.5701. Min Act: -0.0000

Data Index: 1656473 (Python Code)

Max Activating Token Index: 604

Text #14

Max Range: 0.7142. Min Range: -0.7142

Max Act: 0.5839. Min Act: -0.0000

Data Index: 1605677 (Python Code)

Max Activating Token Index: 83

Text #15

Max Range: 0.7142. Min Range: -0.7142

Max Act: 0.5778. Min Act: -0.0000

Data Index: 1366402 (Python Code)

Max Activating Token Index: 489

Text #16

Max Range: 0.7142. Min Range: -0.7142

Max Act: 0.5582. Min Act: -0.0000

Data Index: 1385679 (Python Code)

Max Activating Token Index: 249

Text #17

Max Range: 0.7142. Min Range: -0.7142

Max Act: 0.5584. Min Act: -0.0000

Data Index: 1451465 (Python Code)

Max Activating Token Index: 178

Text #18

Max Range: 0.7142. Min Range: -0.7142

Max Act: 0.5697. Min Act: -0.0000

Data Index: 1550374 (Python Code)

Max Activating Token Index: 304

Text #19

Max Range: 0.7142. Min Range: -0.7142

Max Act: 0.5365. Min Act: -0.0000

Data Index: 1480212 (Python Code)

Max Activating Token Index: 951