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

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

Neuron 2949 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: 1.7383. Min Range: -1.7383

Max Act: 1.7383. Min Act: -0.0001

Data Index: 1473419 (Python Code)

Max Activating Token Index: 142

Text #1

Max Range: 1.7383. Min Range: -1.7383

Max Act: 1.6632. Min Act: -0.0001

Data Index: 1547050 (Python Code)

Max Activating Token Index: 252

Text #2

Max Range: 1.7383. Min Range: -1.7383

Max Act: 1.6359. Min Act: -0.0001

Data Index: 1440983 (Python Code)

Max Activating Token Index: 786

Text #3

Max Range: 1.7383. Min Range: -1.7383

Max Act: 1.6184. Min Act: -0.0000

Data Index: 1423851 (Python Code)

Max Activating Token Index: 273

Text #4

Max Range: 1.7383. Min Range: -1.7383

Max Act: 1.5612. Min Act: -0.0001

Data Index: 1401813 (Python Code)

Max Activating Token Index: 101

Text #5

Max Range: 1.7383. Min Range: -1.7383

Max Act: 1.4457. Min Act: -0.0001

Data Index: 1576347 (Python Code)

Max Activating Token Index: 346

Text #6

Max Range: 1.7383. Min Range: -1.7383

Max Act: 1.3840. Min Act: -0.0001

Data Index: 1383515 (Python Code)

Max Activating Token Index: 428

Text #7

Max Range: 1.7383. Min Range: -1.7383

Max Act: 1.4487. Min Act: -0.0001

Data Index: 1495266 (Python Code)

Max Activating Token Index: 649

Text #8

Max Range: 1.7383. Min Range: -1.7383

Max Act: 1.4516. Min Act: -0.0001

Data Index: 1470000 (Python Code)

Max Activating Token Index: 766

Text #9

Max Range: 1.7383. Min Range: -1.7383

Max Act: 1.2984. Min Act: -0.0001

Data Index: 1598649 (Python Code)

Max Activating Token Index: 494

Text #10

Max Range: 1.7383. Min Range: -1.7383

Max Act: 1.3068. Min Act: -0.0001

Data Index: 1581413 (Python Code)

Max Activating Token Index: 700

Text #11

Max Range: 1.7383. Min Range: -1.7383

Max Act: 1.3068. Min Act: -0.0000

Data Index: 1499610 (Python Code)

Max Activating Token Index: 338

Text #12

Max Range: 1.7383. Min Range: -1.7383

Max Act: 1.3064. Min Act: -0.0001

Data Index: 1425549 (Python Code)

Max Activating Token Index: 67

Text #13

Max Range: 1.7383. Min Range: -1.7383

Max Act: 1.2253. Min Act: -0.0000

Data Index: 1529130 (Python Code)

Max Activating Token Index: 195

Text #14

Max Range: 1.7383. Min Range: -1.7383

Max Act: 1.2466. Min Act: -0.0000

Data Index: 1647029 (Python Code)

Max Activating Token Index: 529

Text #15

Max Range: 1.7383. Min Range: -1.7383

Max Act: 1.3034. Min Act: -0.0001

Data Index: 1414606 (Python Code)

Max Activating Token Index: 849

Text #16

Max Range: 1.7383. Min Range: -1.7383

Max Act: 1.1750. Min Act: -0.0000

Data Index: 1480752 (Python Code)

Max Activating Token Index: 178

Text #17

Max Range: 1.7383. Min Range: -1.7383

Max Act: 1.2781. Min Act: -0.0000

Data Index: 1410223 (Python Code)

Max Activating Token Index: 235

Text #18

Max Range: 1.7383. Min Range: -1.7383

Max Act: 1.2461. Min Act: -0.0000

Data Index: 1609956 (Python Code)

Max Activating Token Index: 244

Text #19

Max Range: 1.7383. Min Range: -1.7383

Max Act: 1.2416. Min Act: -0.0001

Data Index: 1415608 (Python Code)

Max Activating Token Index: 965