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

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

Neuron 2855 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.7327. Min Range: -0.7327

Max Act: 0.7327. Min Act: -0.0000

Data Index: 1608767 (Python Code)

Max Activating Token Index: 876

Text #1

Max Range: 0.7327. Min Range: -0.7327

Max Act: 0.6082. Min Act: -0.0000

Data Index: 1649955 (Python Code)

Max Activating Token Index: 442

Text #2

Max Range: 0.7327. Min Range: -0.7327

Max Act: 0.6344. Min Act: -0.0000

Data Index: 1436002 (Python Code)

Max Activating Token Index: 431

Text #3

Max Range: 0.7327. Min Range: -0.7327

Max Act: 0.6153. Min Act: -0.0000

Data Index: 1570118 (Python Code)

Max Activating Token Index: 836

Text #4

Max Range: 0.7327. Min Range: -0.7327

Max Act: 0.5749. Min Act: -0.0000

Data Index: 1537786 (Python Code)

Max Activating Token Index: 378

Text #5

Max Range: 0.7327. Min Range: -0.7327

Max Act: 0.5243. Min Act: -0.0000

Data Index: 1434366 (Python Code)

Max Activating Token Index: 147

Text #6

Max Range: 0.7327. Min Range: -0.7327

Max Act: 0.5893. Min Act: -0.0000

Data Index: 1430713 (Python Code)

Max Activating Token Index: 914

Text #7

Max Range: 0.7327. Min Range: -0.7327

Max Act: 0.5396. Min Act: -0.0000

Data Index: 1654559 (Python Code)

Max Activating Token Index: 470

Text #8

Max Range: 0.7327. Min Range: -0.7327

Max Act: 0.5023. Min Act: -0.0000

Data Index: 1367101 (Python Code)

Max Activating Token Index: 925

Text #9

Max Range: 0.7327. Min Range: -0.7327

Max Act: 0.5616. Min Act: -0.0000

Data Index: 1469757 (Python Code)

Max Activating Token Index: 792

Text #10

Max Range: 0.7327. Min Range: -0.7327

Max Act: 0.4985. Min Act: -0.0000

Data Index: 1602787 (Python Code)

Max Activating Token Index: 452

Text #11

Max Range: 0.7327. Min Range: -0.7327

Max Act: 0.4990. Min Act: -0.0000

Data Index: 1390991 (Python Code)

Max Activating Token Index: 895

Text #12

Max Range: 0.7327. Min Range: -0.7327

Max Act: 0.5126. Min Act: -0.0000

Data Index: 1648920 (Python Code)

Max Activating Token Index: 764

Text #13

Max Range: 0.7327. Min Range: -0.7327

Max Act: 0.5472. Min Act: -0.0000

Data Index: 1615923 (Python Code)

Max Activating Token Index: 273

Text #14

Max Range: 0.7327. Min Range: -0.7327

Max Act: 0.4997. Min Act: -0.0000

Data Index: 1453755 (Python Code)

Max Activating Token Index: 599

Text #15

Max Range: 0.7327. Min Range: -0.7327

Max Act: 0.5273. Min Act: -0.0000

Data Index: 1432032 (Python Code)

Max Activating Token Index: 940

Text #16

Max Range: 0.7327. Min Range: -0.7327

Max Act: 0.4770. Min Act: -0.0000

Data Index: 1553180 (Python Code)

Max Activating Token Index: 236

Text #17

Max Range: 0.7327. Min Range: -0.7327

Max Act: 0.5093. Min Act: -0.0000

Data Index: 1406893 (Python Code)

Max Activating Token Index: 629

Text #18

Max Range: 0.7327. Min Range: -0.7327

Max Act: 0.5049. Min Act: -0.0000

Data Index: 1463017 (Python Code)

Max Activating Token Index: 541

Text #19

Max Range: 0.7327. Min Range: -0.7327

Max Act: 0.4889. Min Act: -0.0000

Data Index: 1583978 (Python Code)

Max Activating Token Index: 106