Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 6125 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.0519. Min Range: -1.0519

Max Act: 1.0519. Min Act: -0.0001

Data Index: 1618210 (Python Code)

Max Activating Token Index: 233

Text #1

Max Range: 1.0519. Min Range: -1.0519

Max Act: 1.0234. Min Act: -0.0001

Data Index: 1446764 (Python Code)

Max Activating Token Index: 336

Text #2

Max Range: 1.0519. Min Range: -1.0519

Max Act: 1.0352. Min Act: -0.0001

Data Index: 1604736 (Python Code)

Max Activating Token Index: 573

Text #3

Max Range: 1.0519. Min Range: -1.0519

Max Act: 1.0090. Min Act: -0.0001

Data Index: 1577526 (Python Code)

Max Activating Token Index: 314

Text #4

Max Range: 1.0519. Min Range: -1.0519

Max Act: 1.0357. Min Act: -0.0001

Data Index: 1393749 (Python Code)

Max Activating Token Index: 758

Text #5

Max Range: 1.0519. Min Range: -1.0519

Max Act: 1.0309. Min Act: -0.0001

Data Index: 1366595 (Python Code)

Max Activating Token Index: 409

Text #6

Max Range: 1.0519. Min Range: -1.0519

Max Act: 0.9986. Min Act: -0.0001

Data Index: 1630628 (Python Code)

Max Activating Token Index: 91

Text #7

Max Range: 1.0519. Min Range: -1.0519

Max Act: 0.9482. Min Act: -0.0001

Data Index: 1576147 (Python Code)

Max Activating Token Index: 972

Text #8

Max Range: 1.0519. Min Range: -1.0519

Max Act: 1.0250. Min Act: -0.0001

Data Index: 1478007 (Python Code)

Max Activating Token Index: 846

Text #9

Max Range: 1.0519. Min Range: -1.0519

Max Act: 0.8902. Min Act: -0.0001

Data Index: 1375431 (Python Code)

Max Activating Token Index: 1007

Text #10

Max Range: 1.0519. Min Range: -1.0519

Max Act: 0.9007. Min Act: -0.0001

Data Index: 1555252 (Python Code)

Max Activating Token Index: 304

Text #11

Max Range: 1.0519. Min Range: -1.0519

Max Act: 0.9549. Min Act: -0.0001

Data Index: 1442145 (Python Code)

Max Activating Token Index: 735

Text #12

Max Range: 1.0519. Min Range: -1.0519

Max Act: 0.8970. Min Act: -0.0001

Data Index: 1434350 (Python Code)

Max Activating Token Index: 710

Text #13

Max Range: 1.0519. Min Range: -1.0519

Max Act: 0.8552. Min Act: -0.0001

Data Index: 1605313 (Python Code)

Max Activating Token Index: 215

Text #14

Max Range: 1.0519. Min Range: -1.0519

Max Act: 0.9279. Min Act: -0.0001

Data Index: 1542591 (Python Code)

Max Activating Token Index: 284

Text #15

Max Range: 1.0519. Min Range: -1.0519

Max Act: 0.9313. Min Act: -0.0001

Data Index: 1394397 (Python Code)

Max Activating Token Index: 976

Text #16

Max Range: 1.0519. Min Range: -1.0519

Max Act: 0.9050. Min Act: -0.0001

Data Index: 1500958 (Python Code)

Max Activating Token Index: 969

Text #17

Max Range: 1.0519. Min Range: -1.0519

Max Act: 0.8832. Min Act: -0.0001

Data Index: 1566921 (Python Code)

Max Activating Token Index: 984

Text #18

Max Range: 1.0519. Min Range: -1.0519

Max Act: 0.9275. Min Act: -0.0001

Data Index: 1458936 (Python Code)

Max Activating Token Index: 927

Text #19

Max Range: 1.0519. Min Range: -1.0519

Max Act: 0.9103. Min Act: -0.0001

Data Index: 1435499 (Python Code)

Max Activating Token Index: 531