Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 190 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2370. Min Range: -0.2370

Max Act: 0.2209. Min Act: -0.0003

Data Index: 642424 (C4 (Web Text))

Max Activating Token Index: 3

Text #1

Max Range: 0.2370. Min Range: -0.2370

Max Act: 0.1932. Min Act: -0.0003

Data Index: 17005 (C4 (Web Text))

Max Activating Token Index: 961

Text #2

Max Range: 0.2370. Min Range: -0.2370

Max Act: 0.2128. Min Act: -0.0003

Data Index: 605709 (C4 (Web Text))

Max Activating Token Index: 751

Text #3

Max Range: 0.2370. Min Range: -0.2370

Max Act: 0.2370. Min Act: -0.0003

Data Index: 6250 (C4 (Web Text))

Max Activating Token Index: 555

Text #4

Max Range: 0.2370. Min Range: -0.2370

Max Act: 0.2014. Min Act: -0.0003

Data Index: 1197898 (C4 (Web Text))

Max Activating Token Index: 550

Text #5

Max Range: 0.2370. Min Range: -0.2370

Max Act: 0.2089. Min Act: -0.0003

Data Index: 819189 (C4 (Web Text))

Max Activating Token Index: 746

Text #6

Max Range: 0.2370. Min Range: -0.2370

Max Act: 0.2041. Min Act: -0.0003

Data Index: 280064 (C4 (Web Text))

Max Activating Token Index: 489

Text #7

Max Range: 0.2370. Min Range: -0.2370

Max Act: 0.1958. Min Act: -0.0003

Data Index: 401389 (C4 (Web Text))

Max Activating Token Index: 51

Text #8

Max Range: 0.2370. Min Range: -0.2370

Max Act: 0.1968. Min Act: -0.0003

Data Index: 259421 (C4 (Web Text))

Max Activating Token Index: 267

Text #9

Max Range: 0.2370. Min Range: -0.2370

Max Act: 0.1833. Min Act: -0.0003

Data Index: 995725 (C4 (Web Text))

Max Activating Token Index: 604

Text #10

Max Range: 0.2370. Min Range: -0.2370

Max Act: 0.1906. Min Act: -0.0003

Data Index: 1210510 (C4 (Web Text))

Max Activating Token Index: 21

Text #11

Max Range: 0.2370. Min Range: -0.2370

Max Act: 0.1932. Min Act: -0.0003

Data Index: 883654 (C4 (Web Text))

Max Activating Token Index: 99

Text #12

Max Range: 0.2370. Min Range: -0.2370

Max Act: 0.1842. Min Act: -0.0003

Data Index: 545323 (C4 (Web Text))

Max Activating Token Index: 731

Text #13

Max Range: 0.2370. Min Range: -0.2370

Max Act: 0.2046. Min Act: -0.0003

Data Index: 315742 (C4 (Web Text))

Max Activating Token Index: 514

Text #14

Max Range: 0.2370. Min Range: -0.2370

Max Act: 0.1771. Min Act: -0.0003

Data Index: 205463 (C4 (Web Text))

Max Activating Token Index: 5

Text #15

Max Range: 0.2370. Min Range: -0.2370

Max Act: 0.1703. Min Act: -0.0003

Data Index: 1257844 (C4 (Web Text))

Max Activating Token Index: 567

Text #16

Max Range: 0.2370. Min Range: -0.2370

Max Act: 0.1761. Min Act: -0.0003

Data Index: 953492 (C4 (Web Text))

Max Activating Token Index: 797

Text #17

Max Range: 0.2370. Min Range: -0.2370

Max Act: 0.1802. Min Act: -0.0003

Data Index: 23484 (C4 (Web Text))

Max Activating Token Index: 141

Text #18

Max Range: 0.2370. Min Range: -0.2370

Max Act: 0.1940. Min Act: -0.0003

Data Index: 1142712 (C4 (Web Text))

Max Activating Token Index: 354

Text #19

Max Range: 0.2370. Min Range: -0.2370

Max Act: 0.1506. Min Act: -0.0003

Data Index: 146422 (C4 (Web Text))

Max Activating Token Index: 702