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

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

Neuron 2434 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: 3.6058. Min Range: -3.6058

Max Act: 3.6058. Min Act: -0.0000

Data Index: 1475902 (Python Code)

Max Activating Token Index: 879

Text #1

Max Range: 3.6058. Min Range: -3.6058

Max Act: 3.2566. Min Act: -0.0000

Data Index: 1467722 (Python Code)

Max Activating Token Index: 785

Text #2

Max Range: 3.6058. Min Range: -3.6058

Max Act: 3.1050. Min Act: -0.0000

Data Index: 1649359 (Python Code)

Max Activating Token Index: 235

Text #3

Max Range: 3.6058. Min Range: -3.6058

Max Act: 3.2022. Min Act: -0.0000

Data Index: 1380134 (Python Code)

Max Activating Token Index: 381

Text #4

Max Range: 3.6058. Min Range: -3.6058

Max Act: 3.0477. Min Act: -0.0000

Data Index: 1405461 (Python Code)

Max Activating Token Index: 527

Text #5

Max Range: 3.6058. Min Range: -3.6058

Max Act: 3.2146. Min Act: -0.0000

Data Index: 1433408 (Python Code)

Max Activating Token Index: 179

Text #6

Max Range: 3.6058. Min Range: -3.6058

Max Act: 3.0870. Min Act: -0.0000

Data Index: 1538607 (Python Code)

Max Activating Token Index: 72

Text #7

Max Range: 3.6058. Min Range: -3.6058

Max Act: 2.7045. Min Act: -0.0000

Data Index: 1431011 (Python Code)

Max Activating Token Index: 298

Text #8

Max Range: 3.6058. Min Range: -3.6058

Max Act: 3.0038. Min Act: -0.0000

Data Index: 1526811 (Python Code)

Max Activating Token Index: 434

Text #9

Max Range: 3.6058. Min Range: -3.6058

Max Act: 3.0084. Min Act: -0.0000

Data Index: 1465153 (Python Code)

Max Activating Token Index: 480

Text #10

Max Range: 3.6058. Min Range: -3.6058

Max Act: 2.9590. Min Act: -0.0000

Data Index: 1424517 (Python Code)

Max Activating Token Index: 686

Text #11

Max Range: 3.6058. Min Range: -3.6058

Max Act: 2.9555. Min Act: -0.0000

Data Index: 1409784 (Python Code)

Max Activating Token Index: 147

Text #12

Max Range: 3.6058. Min Range: -3.6058

Max Act: 2.7321. Min Act: -0.0000

Data Index: 1604895 (Python Code)

Max Activating Token Index: 204

Text #13

Max Range: 3.6058. Min Range: -3.6058

Max Act: 2.8279. Min Act: -0.0000

Data Index: 1566761 (Python Code)

Max Activating Token Index: 384

Text #14

Max Range: 3.6058. Min Range: -3.6058

Max Act: 2.8074. Min Act: -0.0000

Data Index: 1595720 (Python Code)

Max Activating Token Index: 494

Text #15

Max Range: 3.6058. Min Range: -3.6058

Max Act: 2.8133. Min Act: -0.0000

Data Index: 1468068 (Python Code)

Max Activating Token Index: 122

Text #16

Max Range: 3.6058. Min Range: -3.6058

Max Act: 2.6870. Min Act: -0.0000

Data Index: 1470563 (Python Code)

Max Activating Token Index: 933

Text #17

Max Range: 3.6058. Min Range: -3.6058

Max Act: 2.6973. Min Act: 0.0000

Data Index: 1363806 (Python Code)

Max Activating Token Index: 890

Text #18

Max Range: 3.6058. Min Range: -3.6058

Max Act: 2.6334. Min Act: -0.0000

Data Index: 1434330 (Python Code)

Max Activating Token Index: 104

Text #19

Max Range: 3.6058. Min Range: -3.6058

Max Act: 2.6097. Min Act: -0.0000

Data Index: 1450973 (Python Code)

Max Activating Token Index: 204