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

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

Neuron 4763 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1970. Min Range: -2.1970

Max Act: 2.1970. Min Act: -0.0000

Data Index: 1437055 (Python Code)

Max Activating Token Index: 586

Text #1

Max Range: 2.1970. Min Range: -2.1970

Max Act: 2.0875. Min Act: -0.0000

Data Index: 1407998 (Python Code)

Max Activating Token Index: 960

Text #2

Max Range: 2.1970. Min Range: -2.1970

Max Act: 1.9883. Min Act: -0.0000

Data Index: 1585716 (Python Code)

Max Activating Token Index: 309

Text #3

Max Range: 2.1970. Min Range: -2.1970

Max Act: 1.7892. Min Act: -0.0000

Data Index: 1561981 (Python Code)

Max Activating Token Index: 238

Text #4

Max Range: 2.1970. Min Range: -2.1970

Max Act: 1.7264. Min Act: -0.0000

Data Index: 1492562 (Python Code)

Max Activating Token Index: 170

Text #5

Max Range: 2.1970. Min Range: -2.1970

Max Act: 1.7922. Min Act: -0.0000

Data Index: 1509662 (Python Code)

Max Activating Token Index: 380

Text #6

Max Range: 2.1970. Min Range: -2.1970

Max Act: 1.7776. Min Act: -0.0000

Data Index: 1474701 (Python Code)

Max Activating Token Index: 808

Text #7

Max Range: 2.1970. Min Range: -2.1970

Max Act: 1.7335. Min Act: -0.0000

Data Index: 1397368 (Python Code)

Max Activating Token Index: 385

Text #8

Max Range: 2.1970. Min Range: -2.1970

Max Act: 1.6348. Min Act: -0.0000

Data Index: 1614883 (Python Code)

Max Activating Token Index: 73

Text #9

Max Range: 2.1970. Min Range: -2.1970

Max Act: 1.7271. Min Act: -0.0000

Data Index: 1395115 (Python Code)

Max Activating Token Index: 16

Text #10

Max Range: 2.1970. Min Range: -2.1970

Max Act: 1.8251. Min Act: -0.0000

Data Index: 1362914 (Python Code)

Max Activating Token Index: 266

Text #11

Max Range: 2.1970. Min Range: -2.1970

Max Act: 1.7122. Min Act: -0.0000

Data Index: 1566041 (Python Code)

Max Activating Token Index: 50

Text #12

Max Range: 2.1970. Min Range: -2.1970

Max Act: 1.6025. Min Act: -0.0000

Data Index: 178444 (C4 (Web Text))

Max Activating Token Index: 571

Text #13

Max Range: 2.1970. Min Range: -2.1970

Max Act: 1.4924. Min Act: -0.0000

Data Index: 1651324 (Python Code)

Max Activating Token Index: 855

Text #14

Max Range: 2.1970. Min Range: -2.1970

Max Act: 1.6599. Min Act: -0.0000

Data Index: 1626427 (Python Code)

Max Activating Token Index: 190

Text #15

Max Range: 2.1970. Min Range: -2.1970

Max Act: 1.5343. Min Act: -0.0000

Data Index: 1431621 (Python Code)

Max Activating Token Index: 479

Text #16

Max Range: 2.1970. Min Range: -2.1970

Max Act: 1.5251. Min Act: -0.0000

Data Index: 1400081 (Python Code)

Max Activating Token Index: 689

Text #17

Max Range: 2.1970. Min Range: -2.1970

Max Act: 1.5092. Min Act: -0.0000

Data Index: 1567679 (Python Code)

Max Activating Token Index: 826

Text #18

Max Range: 2.1970. Min Range: -2.1970

Max Act: 1.5965. Min Act: -0.0000

Data Index: 1604998 (Python Code)

Max Activating Token Index: 1000

Text #19

Max Range: 2.1970. Min Range: -2.1970

Max Act: 1.5004. Min Act: -0.0000

Data Index: 242206 (C4 (Web Text))

Max Activating Token Index: 203