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

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

Neuron 4365 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2628. Min Range: -0.2628

Max Act: 0.2628. Min Act: -0.0000

Data Index: 313462 (C4 (Web Text))

Max Activating Token Index: 616

Text #1

Max Range: 0.2628. Min Range: -0.2628

Max Act: 0.2514. Min Act: -0.0000

Data Index: 274399 (C4 (Web Text))

Max Activating Token Index: 421

Text #2

Max Range: 0.2628. Min Range: -0.2628

Max Act: 0.2279. Min Act: -0.0000

Data Index: 562807 (C4 (Web Text))

Max Activating Token Index: 615

Text #3

Max Range: 0.2628. Min Range: -0.2628

Max Act: 0.2188. Min Act: -0.0000

Data Index: 256164 (C4 (Web Text))

Max Activating Token Index: 301

Text #4

Max Range: 0.2628. Min Range: -0.2628

Max Act: 0.2188. Min Act: -0.0000

Data Index: 1328398 (C4 (Web Text))

Max Activating Token Index: 1012

Text #5

Max Range: 0.2628. Min Range: -0.2628

Max Act: 0.2162. Min Act: -0.0000

Data Index: 402904 (C4 (Web Text))

Max Activating Token Index: 322

Text #6

Max Range: 0.2628. Min Range: -0.2628

Max Act: 0.1944. Min Act: -0.0000

Data Index: 341480 (C4 (Web Text))

Max Activating Token Index: 882

Text #7

Max Range: 0.2628. Min Range: -0.2628

Max Act: 0.2123. Min Act: -0.0000

Data Index: 301542 (C4 (Web Text))

Max Activating Token Index: 644

Text #8

Max Range: 0.2628. Min Range: -0.2628

Max Act: 0.2097. Min Act: -0.0000

Data Index: 833983 (C4 (Web Text))

Max Activating Token Index: 904

Text #9

Max Range: 0.2628. Min Range: -0.2628

Max Act: 0.2165. Min Act: -0.0000

Data Index: 930545 (C4 (Web Text))

Max Activating Token Index: 927

Text #10

Max Range: 0.2628. Min Range: -0.2628

Max Act: 0.1818. Min Act: -0.0000

Data Index: 824242 (C4 (Web Text))

Max Activating Token Index: 320

Text #11

Max Range: 0.2628. Min Range: -0.2628

Max Act: 0.1999. Min Act: -0.0000

Data Index: 1186967 (C4 (Web Text))

Max Activating Token Index: 293

Text #12

Max Range: 0.2628. Min Range: -0.2628

Max Act: 0.2041. Min Act: -0.0000

Data Index: 586949 (C4 (Web Text))

Max Activating Token Index: 688

Text #13

Max Range: 0.2628. Min Range: -0.2628

Max Act: 0.1926. Min Act: -0.0000

Data Index: 505092 (C4 (Web Text))

Max Activating Token Index: 944

Text #14

Max Range: 0.2628. Min Range: -0.2628

Max Act: 0.1902. Min Act: -0.0000

Data Index: 43974 (C4 (Web Text))

Max Activating Token Index: 680

Text #15

Max Range: 0.2628. Min Range: -0.2628

Max Act: 0.2084. Min Act: -0.0000

Data Index: 151493 (C4 (Web Text))

Max Activating Token Index: 553

Text #16

Max Range: 0.2628. Min Range: -0.2628

Max Act: 0.1949. Min Act: -0.0000

Data Index: 1152275 (C4 (Web Text))

Max Activating Token Index: 664

Text #17

Max Range: 0.2628. Min Range: -0.2628

Max Act: 0.1971. Min Act: -0.0000

Data Index: 960296 (C4 (Web Text))

Max Activating Token Index: 99

Text #18

Max Range: 0.2628. Min Range: -0.2628

Max Act: 0.1911. Min Act: -0.0000

Data Index: 1225161 (C4 (Web Text))

Max Activating Token Index: 45

Text #19

Max Range: 0.2628. Min Range: -0.2628

Max Act: 0.1972. Min Act: -0.0000

Data Index: 353652 (C4 (Web Text))

Max Activating Token Index: 791