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

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

Neuron 627 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.2308. Min Range: -0.2308

Max Act: 0.2308. Min Act: -0.0002

Data Index: 1336589 (C4 (Web Text))

Max Activating Token Index: 607

Text #1

Max Range: 0.2308. Min Range: -0.2308

Max Act: 0.2245. Min Act: -0.0002

Data Index: 575472 (C4 (Web Text))

Max Activating Token Index: 602

Text #2

Max Range: 0.2308. Min Range: -0.2308

Max Act: 0.2173. Min Act: -0.0002

Data Index: 766934 (C4 (Web Text))

Max Activating Token Index: 862

Text #3

Max Range: 0.2308. Min Range: -0.2308

Max Act: 0.2097. Min Act: -0.0002

Data Index: 1257111 (C4 (Web Text))

Max Activating Token Index: 2

Text #4

Max Range: 0.2308. Min Range: -0.2308

Max Act: 0.2112. Min Act: -0.0001

Data Index: 613584 (C4 (Web Text))

Max Activating Token Index: 328

Text #5

Max Range: 0.2308. Min Range: -0.2308

Max Act: 0.2081. Min Act: -0.0002

Data Index: 728554 (C4 (Web Text))

Max Activating Token Index: 959

Text #6

Max Range: 0.2308. Min Range: -0.2308

Max Act: 0.2040. Min Act: -0.0002

Data Index: 1217279 (C4 (Web Text))

Max Activating Token Index: 240

Text #7

Max Range: 0.2308. Min Range: -0.2308

Max Act: 0.1986. Min Act: -0.0002

Data Index: 1268822 (C4 (Web Text))

Max Activating Token Index: 944

Text #8

Max Range: 0.2308. Min Range: -0.2308

Max Act: 0.1942. Min Act: -0.0002

Data Index: 602707 (C4 (Web Text))

Max Activating Token Index: 937

Text #9

Max Range: 0.2308. Min Range: -0.2308

Max Act: 0.1952. Min Act: -0.0002

Data Index: 477783 (C4 (Web Text))

Max Activating Token Index: 7

Text #10

Max Range: 0.2308. Min Range: -0.2308

Max Act: 0.1958. Min Act: -0.0002

Data Index: 419835 (C4 (Web Text))

Max Activating Token Index: 963

Text #11

Max Range: 0.2308. Min Range: -0.2308

Max Act: 0.1937. Min Act: -0.0002

Data Index: 1211553 (C4 (Web Text))

Max Activating Token Index: 314

Text #12

Max Range: 0.2308. Min Range: -0.2308

Max Act: 0.1904. Min Act: -0.0002

Data Index: 93888 (C4 (Web Text))

Max Activating Token Index: 661

Text #13

Max Range: 0.2308. Min Range: -0.2308

Max Act: 0.1838. Min Act: -0.0002

Data Index: 1059029 (C4 (Web Text))

Max Activating Token Index: 803

Text #14

Max Range: 0.2308. Min Range: -0.2308

Max Act: 0.1795. Min Act: -0.0002

Data Index: 626573 (C4 (Web Text))

Max Activating Token Index: 935

Text #15

Max Range: 0.2308. Min Range: -0.2308

Max Act: 0.1788. Min Act: -0.0002

Data Index: 830139 (C4 (Web Text))

Max Activating Token Index: 57

Text #16

Max Range: 0.2308. Min Range: -0.2308

Max Act: 0.1769. Min Act: -0.0002

Data Index: 62563 (C4 (Web Text))

Max Activating Token Index: 3

Text #17

Max Range: 0.2308. Min Range: -0.2308

Max Act: 0.1836. Min Act: -0.0002

Data Index: 990163 (C4 (Web Text))

Max Activating Token Index: 15

Text #18

Max Range: 0.2308. Min Range: -0.2308

Max Act: 0.1798. Min Act: -0.0002

Data Index: 871035 (C4 (Web Text))

Max Activating Token Index: 75

Text #19

Max Range: 0.2308. Min Range: -0.2308

Max Act: 0.1779. Min Act: -0.0002

Data Index: 1090118 (C4 (Web Text))

Max Activating Token Index: 872