Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4677 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.2969. Min Range: -0.2969

Max Act: 0.2969. Min Act: -0.0000

Data Index: 208234 (C4 (Web Text))

Max Activating Token Index: 712

Text #1

Max Range: 0.2969. Min Range: -0.2969

Max Act: 0.2478. Min Act: -0.0000

Data Index: 283937 (C4 (Web Text))

Max Activating Token Index: 604

Text #2

Max Range: 0.2969. Min Range: -0.2969

Max Act: 0.2478. Min Act: 0.0000

Data Index: 175015 (C4 (Web Text))

Max Activating Token Index: 278

Text #3

Max Range: 0.2969. Min Range: -0.2969

Max Act: 0.2240. Min Act: -0.0000

Data Index: 454407 (C4 (Web Text))

Max Activating Token Index: 857

Text #4

Max Range: 0.2969. Min Range: -0.2969

Max Act: 0.2258. Min Act: -0.0000

Data Index: 305512 (C4 (Web Text))

Max Activating Token Index: 1019

Text #5

Max Range: 0.2969. Min Range: -0.2969

Max Act: 0.2337. Min Act: -0.0000

Data Index: 101236 (C4 (Web Text))

Max Activating Token Index: 604

Text #6

Max Range: 0.2969. Min Range: -0.2969

Max Act: 0.1947. Min Act: -0.0000

Data Index: 748609 (C4 (Web Text))

Max Activating Token Index: 693

Text #7

Max Range: 0.2969. Min Range: -0.2969

Max Act: 0.2116. Min Act: -0.0000

Data Index: 1109489 (C4 (Web Text))

Max Activating Token Index: 472

Text #8

Max Range: 0.2969. Min Range: -0.2969

Max Act: 0.2031. Min Act: -0.0000

Data Index: 246264 (C4 (Web Text))

Max Activating Token Index: 708

Text #9

Max Range: 0.2969. Min Range: -0.2969

Max Act: 0.1938. Min Act: -0.0000

Data Index: 519453 (C4 (Web Text))

Max Activating Token Index: 200

Text #10

Max Range: 0.2969. Min Range: -0.2969

Max Act: 0.2083. Min Act: -0.0000

Data Index: 1026743 (C4 (Web Text))

Max Activating Token Index: 650

Text #11

Max Range: 0.2969. Min Range: -0.2969

Max Act: 0.1856. Min Act: -0.0000

Data Index: 1086240 (C4 (Web Text))

Max Activating Token Index: 963

Text #12

Max Range: 0.2969. Min Range: -0.2969

Max Act: 0.1965. Min Act: -0.0000

Data Index: 144088 (C4 (Web Text))

Max Activating Token Index: 98

Text #13

Max Range: 0.2969. Min Range: -0.2969

Max Act: 0.1952. Min Act: -0.0000

Data Index: 614296 (C4 (Web Text))

Max Activating Token Index: 835

Text #14

Max Range: 0.2969. Min Range: -0.2969

Max Act: 0.1811. Min Act: -0.0000

Data Index: 1139104 (C4 (Web Text))

Max Activating Token Index: 244

Text #15

Max Range: 0.2969. Min Range: -0.2969

Max Act: 0.1795. Min Act: 0.0000

Data Index: 717010 (C4 (Web Text))

Max Activating Token Index: 449

Text #16

Max Range: 0.2969. Min Range: -0.2969

Max Act: 0.1860. Min Act: 0.0000

Data Index: 77907 (C4 (Web Text))

Max Activating Token Index: 518

Text #17

Max Range: 0.2969. Min Range: -0.2969

Max Act: 0.1847. Min Act: -0.0000

Data Index: 1267682 (C4 (Web Text))

Max Activating Token Index: 373

Text #18

Max Range: 0.2969. Min Range: -0.2969

Max Act: 0.1790. Min Act: -0.0000

Data Index: 1287794 (C4 (Web Text))

Max Activating Token Index: 611

Text #19

Max Range: 0.2969. Min Range: -0.2969

Max Act: 0.1838. Min Act: -0.0000

Data Index: 363879 (C4 (Web Text))

Max Activating Token Index: 190