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

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

Neuron 1430 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7910. Min Range: -0.7910

Max Act: 0.7910. Min Act: -0.0000

Data Index: 1250489 (C4 (Web Text))

Max Activating Token Index: 709

Text #1

Max Range: 0.7910. Min Range: -0.7910

Max Act: 0.6921. Min Act: -0.0001

Data Index: 1560453 (Python Code)

Max Activating Token Index: 492

Text #2

Max Range: 0.7910. Min Range: -0.7910

Max Act: 0.6121. Min Act: -0.0001

Data Index: 1471648 (Python Code)

Max Activating Token Index: 533

Text #3

Max Range: 0.7910. Min Range: -0.7910

Max Act: 0.6541. Min Act: -0.0000

Data Index: 1651700 (Python Code)

Max Activating Token Index: 383

Text #4

Max Range: 0.7910. Min Range: -0.7910

Max Act: 0.6083. Min Act: -0.0001

Data Index: 1475355 (Python Code)

Max Activating Token Index: 731

Text #5

Max Range: 0.7910. Min Range: -0.7910

Max Act: 0.6320. Min Act: -0.0000

Data Index: 1604077 (Python Code)

Max Activating Token Index: 959

Text #6

Max Range: 0.7910. Min Range: -0.7910

Max Act: 0.6001. Min Act: -0.0001

Data Index: 1545999 (Python Code)

Max Activating Token Index: 231

Text #7

Max Range: 0.7910. Min Range: -0.7910

Max Act: 0.5762. Min Act: -0.0001

Data Index: 1626838 (Python Code)

Max Activating Token Index: 453

Text #8

Max Range: 0.7910. Min Range: -0.7910

Max Act: 0.5490. Min Act: -0.0001

Data Index: 1483494 (Python Code)

Max Activating Token Index: 196

Text #9

Max Range: 0.7910. Min Range: -0.7910

Max Act: 0.5930. Min Act: -0.0001

Data Index: 1478073 (Python Code)

Max Activating Token Index: 185

Text #10

Max Range: 0.7910. Min Range: -0.7910

Max Act: 0.5508. Min Act: -0.0000

Data Index: 651832 (C4 (Web Text))

Max Activating Token Index: 123

Text #11

Max Range: 0.7910. Min Range: -0.7910

Max Act: 0.5430. Min Act: -0.0000

Data Index: 1517412 (Python Code)

Max Activating Token Index: 54

Text #12

Max Range: 0.7910. Min Range: -0.7910

Max Act: 0.5642. Min Act: -0.0001

Data Index: 1363520 (Python Code)

Max Activating Token Index: 540

Text #13

Max Range: 0.7910. Min Range: -0.7910

Max Act: 0.5174. Min Act: -0.0001

Data Index: 1621110 (Python Code)

Max Activating Token Index: 274

Text #14

Max Range: 0.7910. Min Range: -0.7910

Max Act: 0.5438. Min Act: -0.0000

Data Index: 1525877 (Python Code)

Max Activating Token Index: 394

Text #15

Max Range: 0.7910. Min Range: -0.7910

Max Act: 0.4457. Min Act: -0.0000

Data Index: 605325 (C4 (Web Text))

Max Activating Token Index: 133

Text #16

Max Range: 0.7910. Min Range: -0.7910

Max Act: 0.5298. Min Act: -0.0000

Data Index: 875108 (C4 (Web Text))

Max Activating Token Index: 939

Text #17

Max Range: 0.7910. Min Range: -0.7910

Max Act: 0.5011. Min Act: -0.0001

Data Index: 1397375 (Python Code)

Max Activating Token Index: 281

Text #18

Max Range: 0.7910. Min Range: -0.7910

Max Act: 0.5225. Min Act: -0.0001

Data Index: 1463868 (Python Code)

Max Activating Token Index: 1017

Text #19

Max Range: 0.7910. Min Range: -0.7910

Max Act: 0.4994. Min Act: -0.0000

Data Index: 1628831 (Python Code)

Max Activating Token Index: 91