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

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

Neuron 3913 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: 0.2208. Min Range: -0.2208

Max Act: 0.2198. Min Act: -0.0001

Data Index: 1531824 (Python Code)

Max Activating Token Index: 267

Text #1

Max Range: 0.2208. Min Range: -0.2208

Max Act: 0.2155. Min Act: -0.0001

Data Index: 1508853 (Python Code)

Max Activating Token Index: 311

Text #2

Max Range: 0.2208. Min Range: -0.2208

Max Act: 0.2208. Min Act: -0.0001

Data Index: 130009 (C4 (Web Text))

Max Activating Token Index: 365

Text #3

Max Range: 0.2208. Min Range: -0.2208

Max Act: 0.2058. Min Act: -0.0001

Data Index: 1486541 (Python Code)

Max Activating Token Index: 198

Text #4

Max Range: 0.2208. Min Range: -0.2208

Max Act: 0.2037. Min Act: -0.0001

Data Index: 646214 (C4 (Web Text))

Max Activating Token Index: 925

Text #5

Max Range: 0.2208. Min Range: -0.2208

Max Act: 0.1993. Min Act: -0.0001

Data Index: 284602 (C4 (Web Text))

Max Activating Token Index: 582

Text #6

Max Range: 0.2208. Min Range: -0.2208

Max Act: 0.1936. Min Act: -0.0001

Data Index: 145989 (C4 (Web Text))

Max Activating Token Index: 902

Text #7

Max Range: 0.2208. Min Range: -0.2208

Max Act: 0.1894. Min Act: -0.0001

Data Index: 1604084 (Python Code)

Max Activating Token Index: 619

Text #8

Max Range: 0.2208. Min Range: -0.2208

Max Act: 0.1831. Min Act: -0.0001

Data Index: 1414965 (Python Code)

Max Activating Token Index: 123

Text #9

Max Range: 0.2208. Min Range: -0.2208

Max Act: 0.1630. Min Act: -0.0001

Data Index: 1497086 (Python Code)

Max Activating Token Index: 179

Text #10

Max Range: 0.2208. Min Range: -0.2208

Max Act: 0.1764. Min Act: -0.0001

Data Index: 1142170 (C4 (Web Text))

Max Activating Token Index: 576

Text #11

Max Range: 0.2208. Min Range: -0.2208

Max Act: 0.1709. Min Act: -0.0001

Data Index: 1529418 (Python Code)

Max Activating Token Index: 295

Text #12

Max Range: 0.2208. Min Range: -0.2208

Max Act: 0.1794. Min Act: -0.0001

Data Index: 464270 (C4 (Web Text))

Max Activating Token Index: 560

Text #13

Max Range: 0.2208. Min Range: -0.2208

Max Act: 0.1771. Min Act: -0.0001

Data Index: 682383 (C4 (Web Text))

Max Activating Token Index: 730

Text #14

Max Range: 0.2208. Min Range: -0.2208

Max Act: 0.1841. Min Act: -0.0001

Data Index: 740815 (C4 (Web Text))

Max Activating Token Index: 310

Text #15

Max Range: 0.2208. Min Range: -0.2208

Max Act: 0.1570. Min Act: -0.0001

Data Index: 1382524 (Python Code)

Max Activating Token Index: 123

Text #16

Max Range: 0.2208. Min Range: -0.2208

Max Act: 0.1645. Min Act: -0.0001

Data Index: 1545621 (Python Code)

Max Activating Token Index: 829

Text #17

Max Range: 0.2208. Min Range: -0.2208

Max Act: 0.1678. Min Act: -0.0001

Data Index: 1525563 (Python Code)

Max Activating Token Index: 267

Text #18

Max Range: 0.2208. Min Range: -0.2208

Max Act: 0.1595. Min Act: -0.0001

Data Index: 1390999 (Python Code)

Max Activating Token Index: 487

Text #19

Max Range: 0.2208. Min Range: -0.2208

Max Act: 0.1666. Min Act: -0.0001

Data Index: 1530539 (Python Code)

Max Activating Token Index: 213