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

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

Neuron 920 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3389. Min Range: -1.3389

Max Act: 1.3328. Min Act: -0.0000

Data Index: 1640234 (Python Code)

Max Activating Token Index: 428

Text #1

Max Range: 1.3389. Min Range: -1.3389

Max Act: 1.3389. Min Act: -0.0000

Data Index: 1628045 (Python Code)

Max Activating Token Index: 141

Text #2

Max Range: 1.3389. Min Range: -1.3389

Max Act: 1.1172. Min Act: -0.0000

Data Index: 1598851 (Python Code)

Max Activating Token Index: 338

Text #3

Max Range: 1.3389. Min Range: -1.3389

Max Act: 1.0536. Min Act: -0.0000

Data Index: 390679 (C4 (Web Text))

Max Activating Token Index: 604

Text #4

Max Range: 1.3389. Min Range: -1.3389

Max Act: 0.9182. Min Act: -0.0000

Data Index: 1645788 (Python Code)

Max Activating Token Index: 805

Text #5

Max Range: 1.3389. Min Range: -1.3389

Max Act: 1.0279. Min Act: -0.0000

Data Index: 1434484 (Python Code)

Max Activating Token Index: 752

Text #6

Max Range: 1.3389. Min Range: -1.3389

Max Act: 0.9536. Min Act: -0.0000

Data Index: 1424541 (Python Code)

Max Activating Token Index: 904

Text #7

Max Range: 1.3389. Min Range: -1.3389

Max Act: 0.8655. Min Act: -0.0000

Data Index: 1389312 (Python Code)

Max Activating Token Index: 694

Text #8

Max Range: 1.3389. Min Range: -1.3389

Max Act: 0.8460. Min Act: -0.0000

Data Index: 1414653 (Python Code)

Max Activating Token Index: 897

Text #9

Max Range: 1.3389. Min Range: -1.3389

Max Act: 0.8718. Min Act: -0.0000

Data Index: 1378346 (Python Code)

Max Activating Token Index: 286

Text #10

Max Range: 1.3389. Min Range: -1.3389

Max Act: 0.8925. Min Act: -0.0000

Data Index: 1399090 (Python Code)

Max Activating Token Index: 7

Text #11

Max Range: 1.3389. Min Range: -1.3389

Max Act: 0.8361. Min Act: -0.0000

Data Index: 1479376 (Python Code)

Max Activating Token Index: 954

Text #12

Max Range: 1.3389. Min Range: -1.3389

Max Act: 0.8500. Min Act: -0.0000

Data Index: 1467381 (Python Code)

Max Activating Token Index: 265

Text #13

Max Range: 1.3389. Min Range: -1.3389

Max Act: 0.8646. Min Act: -0.0000

Data Index: 1502398 (Python Code)

Max Activating Token Index: 295

Text #14

Max Range: 1.3389. Min Range: -1.3389

Max Act: 0.8074. Min Act: -0.0000

Data Index: 757445 (C4 (Web Text))

Max Activating Token Index: 567

Text #15

Max Range: 1.3389. Min Range: -1.3389

Max Act: 0.7649. Min Act: -0.0000

Data Index: 1606078 (Python Code)

Max Activating Token Index: 436

Text #16

Max Range: 1.3389. Min Range: -1.3389

Max Act: 0.8378. Min Act: -0.0000

Data Index: 1607991 (Python Code)

Max Activating Token Index: 203

Text #17

Max Range: 1.3389. Min Range: -1.3389

Max Act: 0.8000. Min Act: -0.0000

Data Index: 1623402 (Python Code)

Max Activating Token Index: 980

Text #18

Max Range: 1.3389. Min Range: -1.3389

Max Act: 0.8489. Min Act: -0.0000

Data Index: 1003292 (C4 (Web Text))

Max Activating Token Index: 213

Text #19

Max Range: 1.3389. Min Range: -1.3389

Max Act: 0.8378. Min Act: -0.0000

Data Index: 1649477 (Python Code)

Max Activating Token Index: 67