Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3462 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2208. Min Range: -0.2208

Max Act: 0.2160. Min Act: -0.0000

Data Index: 680473 (C4 (Web Text))

Max Activating Token Index: 516

Text #1

Max Range: 0.2208. Min Range: -0.2208

Max Act: 0.2208. Min Act: -0.0000

Data Index: 1328652 (C4 (Web Text))

Max Activating Token Index: 616

Text #2

Max Range: 0.2208. Min Range: -0.2208

Max Act: 0.1940. Min Act: -0.0001

Data Index: 1229770 (C4 (Web Text))

Max Activating Token Index: 750

Text #3

Max Range: 0.2208. Min Range: -0.2208

Max Act: 0.2061. Min Act: -0.0001

Data Index: 1572931 (Python Code)

Max Activating Token Index: 102

Text #4

Max Range: 0.2208. Min Range: -0.2208

Max Act: 0.1978. Min Act: -0.0000

Data Index: 568608 (C4 (Web Text))

Max Activating Token Index: 523

Text #5

Max Range: 0.2208. Min Range: -0.2208

Max Act: 0.2054. Min Act: -0.0001

Data Index: 874506 (C4 (Web Text))

Max Activating Token Index: 84

Text #6

Max Range: 0.2208. Min Range: -0.2208

Max Act: 0.1798. Min Act: -0.0000

Data Index: 1273799 (C4 (Web Text))

Max Activating Token Index: 670

Text #7

Max Range: 0.2208. Min Range: -0.2208

Max Act: 0.1939. Min Act: -0.0001

Data Index: 927852 (C4 (Web Text))

Max Activating Token Index: 83

Text #8

Max Range: 0.2208. Min Range: -0.2208

Max Act: 0.1910. Min Act: -0.0001

Data Index: 770812 (C4 (Web Text))

Max Activating Token Index: 73

Text #9

Max Range: 0.2208. Min Range: -0.2208

Max Act: 0.1703. Min Act: -0.0001

Data Index: 152433 (C4 (Web Text))

Max Activating Token Index: 501

Text #10

Max Range: 0.2208. Min Range: -0.2208

Max Act: 0.1887. Min Act: -0.0001

Data Index: 1477751 (Python Code)

Max Activating Token Index: 700

Text #11

Max Range: 0.2208. Min Range: -0.2208

Max Act: 0.1876. Min Act: -0.0001

Data Index: 1562242 (Python Code)

Max Activating Token Index: 498

Text #12

Max Range: 0.2208. Min Range: -0.2208

Max Act: 0.1871. Min Act: -0.0001

Data Index: 1499722 (Python Code)

Max Activating Token Index: 999

Text #13

Max Range: 0.2208. Min Range: -0.2208

Max Act: 0.1809. Min Act: -0.0001

Data Index: 254331 (C4 (Web Text))

Max Activating Token Index: 134

Text #14

Max Range: 0.2208. Min Range: -0.2208

Max Act: 0.1932. Min Act: -0.0001

Data Index: 1237110 (C4 (Web Text))

Max Activating Token Index: 91

Text #15

Max Range: 0.2208. Min Range: -0.2208

Max Act: 0.1820. Min Act: -0.0001

Data Index: 934147 (C4 (Web Text))

Max Activating Token Index: 138

Text #16

Max Range: 0.2208. Min Range: -0.2208

Max Act: 0.1847. Min Act: -0.0001

Data Index: 1484066 (Python Code)

Max Activating Token Index: 810

Text #17

Max Range: 0.2208. Min Range: -0.2208

Max Act: 0.1824. Min Act: -0.0001

Data Index: 939052 (C4 (Web Text))

Max Activating Token Index: 963

Text #18

Max Range: 0.2208. Min Range: -0.2208

Max Act: 0.1840. Min Act: -0.0001

Data Index: 1625602 (Python Code)

Max Activating Token Index: 742

Text #19

Max Range: 0.2208. Min Range: -0.2208

Max Act: 0.1781. Min Act: -0.0001

Data Index: 229598 (C4 (Web Text))

Max Activating Token Index: 812