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

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

Neuron 1468 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: 0.7071. Min Range: -0.7071

Max Act: 0.7071. Min Act: -0.0000

Data Index: 1450470 (Python Code)

Max Activating Token Index: 227

Text #1

Max Range: 0.7071. Min Range: -0.7071

Max Act: 0.6542. Min Act: -0.0000

Data Index: 229486 (C4 (Web Text))

Max Activating Token Index: 629

Text #2

Max Range: 0.7071. Min Range: -0.7071

Max Act: 0.6949. Min Act: -0.0000

Data Index: 964016 (C4 (Web Text))

Max Activating Token Index: 927

Text #3

Max Range: 0.7071. Min Range: -0.7071

Max Act: 0.6404. Min Act: -0.0000

Data Index: 545073 (C4 (Web Text))

Max Activating Token Index: 163

Text #4

Max Range: 0.7071. Min Range: -0.7071

Max Act: 0.5944. Min Act: -0.0000

Data Index: 1419104 (Python Code)

Max Activating Token Index: 777

Text #5

Max Range: 0.7071. Min Range: -0.7071

Max Act: 0.5490. Min Act: -0.0000

Data Index: 1445461 (Python Code)

Max Activating Token Index: 914

Text #6

Max Range: 0.7071. Min Range: -0.7071

Max Act: 0.5578. Min Act: -0.0000

Data Index: 1386098 (Python Code)

Max Activating Token Index: 733

Text #7

Max Range: 0.7071. Min Range: -0.7071

Max Act: 0.5476. Min Act: -0.0000

Data Index: 1424134 (Python Code)

Max Activating Token Index: 1014

Text #8

Max Range: 0.7071. Min Range: -0.7071

Max Act: 0.5521. Min Act: -0.0000

Data Index: 1549601 (Python Code)

Max Activating Token Index: 644

Text #9

Max Range: 0.7071. Min Range: -0.7071

Max Act: 0.5430. Min Act: -0.0000

Data Index: 1131027 (C4 (Web Text))

Max Activating Token Index: 625

Text #10

Max Range: 0.7071. Min Range: -0.7071

Max Act: 0.5613. Min Act: -0.0000

Data Index: 548225 (C4 (Web Text))

Max Activating Token Index: 303

Text #11

Max Range: 0.7071. Min Range: -0.7071

Max Act: 0.5317. Min Act: -0.0000

Data Index: 1241333 (C4 (Web Text))

Max Activating Token Index: 449

Text #12

Max Range: 0.7071. Min Range: -0.7071

Max Act: 0.5117. Min Act: -0.0000

Data Index: 1218151 (C4 (Web Text))

Max Activating Token Index: 532

Text #13

Max Range: 0.7071. Min Range: -0.7071

Max Act: 0.5394. Min Act: -0.0000

Data Index: 264667 (C4 (Web Text))

Max Activating Token Index: 936

Text #14

Max Range: 0.7071. Min Range: -0.7071

Max Act: 0.5191. Min Act: -0.0000

Data Index: 1605316 (Python Code)

Max Activating Token Index: 656

Text #15

Max Range: 0.7071. Min Range: -0.7071

Max Act: 0.5169. Min Act: -0.0000

Data Index: 1434372 (Python Code)

Max Activating Token Index: 113

Text #16

Max Range: 0.7071. Min Range: -0.7071

Max Act: 0.5121. Min Act: -0.0000

Data Index: 585380 (C4 (Web Text))

Max Activating Token Index: 487

Text #17

Max Range: 0.7071. Min Range: -0.7071

Max Act: 0.5233. Min Act: -0.0000

Data Index: 1596021 (Python Code)

Max Activating Token Index: 51

Text #18

Max Range: 0.7071. Min Range: -0.7071

Max Act: 0.4872. Min Act: -0.0000

Data Index: 142865 (C4 (Web Text))

Max Activating Token Index: 761

Text #19

Max Range: 0.7071. Min Range: -0.7071

Max Act: 0.4548. Min Act: -0.0000

Data Index: 1568033 (Python Code)

Max Activating Token Index: 203