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

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

Neuron 1179 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.2617. Min Range: -0.2617

Max Act: 0.2539. Min Act: -0.0001

Data Index: 633481 (C4 (Web Text))

Max Activating Token Index: 168

Text #1

Max Range: 0.2617. Min Range: -0.2617

Max Act: 0.2617. Min Act: -0.0001

Data Index: 684395 (C4 (Web Text))

Max Activating Token Index: 8

Text #2

Max Range: 0.2617. Min Range: -0.2617

Max Act: 0.2253. Min Act: -0.0001

Data Index: 304269 (C4 (Web Text))

Max Activating Token Index: 149

Text #3

Max Range: 0.2617. Min Range: -0.2617

Max Act: 0.1977. Min Act: -0.0001

Data Index: 221562 (C4 (Web Text))

Max Activating Token Index: 894

Text #4

Max Range: 0.2617. Min Range: -0.2617

Max Act: 0.1947. Min Act: -0.0001

Data Index: 88010 (C4 (Web Text))

Max Activating Token Index: 881

Text #5

Max Range: 0.2617. Min Range: -0.2617

Max Act: 0.1927. Min Act: -0.0001

Data Index: 858111 (C4 (Web Text))

Max Activating Token Index: 668

Text #6

Max Range: 0.2617. Min Range: -0.2617

Max Act: 0.1892. Min Act: -0.0001

Data Index: 953471 (C4 (Web Text))

Max Activating Token Index: 767

Text #7

Max Range: 0.2617. Min Range: -0.2617

Max Act: 0.1899. Min Act: -0.0001

Data Index: 99925 (C4 (Web Text))

Max Activating Token Index: 1013

Text #8

Max Range: 0.2617. Min Range: -0.2617

Max Act: 0.1934. Min Act: -0.0001

Data Index: 1106095 (C4 (Web Text))

Max Activating Token Index: 174

Text #9

Max Range: 0.2617. Min Range: -0.2617

Max Act: 0.1794. Min Act: -0.0001

Data Index: 1196466 (C4 (Web Text))

Max Activating Token Index: 137

Text #10

Max Range: 0.2617. Min Range: -0.2617

Max Act: 0.1789. Min Act: -0.0001

Data Index: 1297629 (C4 (Web Text))

Max Activating Token Index: 957

Text #11

Max Range: 0.2617. Min Range: -0.2617

Max Act: 0.1800. Min Act: -0.0001

Data Index: 855587 (C4 (Web Text))

Max Activating Token Index: 443

Text #12

Max Range: 0.2617. Min Range: -0.2617

Max Act: 0.1740. Min Act: -0.0001

Data Index: 363501 (C4 (Web Text))

Max Activating Token Index: 832

Text #13

Max Range: 0.2617. Min Range: -0.2617

Max Act: 0.1707. Min Act: -0.0001

Data Index: 1410542 (Python Code)

Max Activating Token Index: 552

Text #14

Max Range: 0.2617. Min Range: -0.2617

Max Act: 0.1724. Min Act: -0.0001

Data Index: 1509357 (Python Code)

Max Activating Token Index: 425

Text #15

Max Range: 0.2617. Min Range: -0.2617

Max Act: 0.1651. Min Act: -0.0001

Data Index: 977273 (C4 (Web Text))

Max Activating Token Index: 377

Text #16

Max Range: 0.2617. Min Range: -0.2617

Max Act: 0.1612. Min Act: -0.0001

Data Index: 1374417 (Python Code)

Max Activating Token Index: 467

Text #17

Max Range: 0.2617. Min Range: -0.2617

Max Act: 0.1550. Min Act: -0.0001

Data Index: 1012679 (C4 (Web Text))

Max Activating Token Index: 147

Text #18

Max Range: 0.2617. Min Range: -0.2617

Max Act: 0.1489. Min Act: -0.0001

Data Index: 996213 (C4 (Web Text))

Max Activating Token Index: 611

Text #19

Max Range: 0.2617. Min Range: -0.2617

Max Act: 0.1597. Min Act: -0.0001

Data Index: 153704 (C4 (Web Text))

Max Activating Token Index: 56