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

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

Neuron 3152 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: 0.2646. Min Range: -0.2646

Max Act: 0.2646. Min Act: -0.0000

Data Index: 1630028 (Python Code)

Max Activating Token Index: 649

Text #1

Max Range: 0.2646. Min Range: -0.2646

Max Act: 0.2600. Min Act: -0.0000

Data Index: 1521638 (Python Code)

Max Activating Token Index: 159

Text #2

Max Range: 0.2646. Min Range: -0.2646

Max Act: 0.2358. Min Act: 0.0000

Data Index: 1457708 (Python Code)

Max Activating Token Index: 198

Text #3

Max Range: 0.2646. Min Range: -0.2646

Max Act: 0.2531. Min Act: 0.0001

Data Index: 1382469 (Python Code)

Max Activating Token Index: 282

Text #4

Max Range: 0.2646. Min Range: -0.2646

Max Act: 0.2419. Min Act: -0.0000

Data Index: 1604344 (Python Code)

Max Activating Token Index: 333

Text #5

Max Range: 0.2646. Min Range: -0.2646

Max Act: 0.2474. Min Act: 0.0000

Data Index: 1613156 (Python Code)

Max Activating Token Index: 82

Text #6

Max Range: 0.2646. Min Range: -0.2646

Max Act: 0.2288. Min Act: -0.0000

Data Index: 1555110 (Python Code)

Max Activating Token Index: 268

Text #7

Max Range: 0.2646. Min Range: -0.2646

Max Act: 0.2298. Min Act: -0.0000

Data Index: 1417308 (Python Code)

Max Activating Token Index: 971

Text #8

Max Range: 0.2646. Min Range: -0.2646

Max Act: 0.2218. Min Act: -0.0000

Data Index: 1617071 (Python Code)

Max Activating Token Index: 367

Text #9

Max Range: 0.2646. Min Range: -0.2646

Max Act: 0.2215. Min Act: -0.0000

Data Index: 1457473 (Python Code)

Max Activating Token Index: 363

Text #10

Max Range: 0.2646. Min Range: -0.2646

Max Act: 0.2196. Min Act: -0.0000

Data Index: 1470409 (Python Code)

Max Activating Token Index: 379

Text #11

Max Range: 0.2646. Min Range: -0.2646

Max Act: 0.2175. Min Act: -0.0000

Data Index: 1531590 (Python Code)

Max Activating Token Index: 473

Text #12

Max Range: 0.2646. Min Range: -0.2646

Max Act: 0.2039. Min Act: 0.0000

Data Index: 1616087 (Python Code)

Max Activating Token Index: 84

Text #13

Max Range: 0.2646. Min Range: -0.2646

Max Act: 0.2101. Min Act: -0.0000

Data Index: 1497819 (Python Code)

Max Activating Token Index: 325

Text #14

Max Range: 0.2646. Min Range: -0.2646

Max Act: 0.2083. Min Act: -0.0000

Data Index: 1527324 (Python Code)

Max Activating Token Index: 407

Text #15

Max Range: 0.2646. Min Range: -0.2646

Max Act: 0.2010. Min Act: -0.0000

Data Index: 1489506 (Python Code)

Max Activating Token Index: 162

Text #16

Max Range: 0.2646. Min Range: -0.2646

Max Act: 0.2069. Min Act: 0.0001

Data Index: 1632800 (Python Code)

Max Activating Token Index: 581

Text #17

Max Range: 0.2646. Min Range: -0.2646

Max Act: 0.2128. Min Act: -0.0000

Data Index: 1537505 (Python Code)

Max Activating Token Index: 542

Text #18

Max Range: 0.2646. Min Range: -0.2646

Max Act: 0.2047. Min Act: -0.0000

Data Index: 1459047 (Python Code)

Max Activating Token Index: 143

Text #19

Max Range: 0.2646. Min Range: -0.2646

Max Act: 0.2122. Min Act: -0.0000

Data Index: 1635923 (Python Code)

Max Activating Token Index: 395