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

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

Neuron 3501 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: 0.2989. Min Range: -0.2989

Max Act: 0.2989. Min Act: -0.0000

Data Index: 325506 (C4 (Web Text))

Max Activating Token Index: 126

Text #1

Max Range: 0.2989. Min Range: -0.2989

Max Act: 0.2835. Min Act: -0.0000

Data Index: 628404 (C4 (Web Text))

Max Activating Token Index: 589

Text #2

Max Range: 0.2989. Min Range: -0.2989

Max Act: 0.2370. Min Act: -0.0000

Data Index: 175331 (C4 (Web Text))

Max Activating Token Index: 553

Text #3

Max Range: 0.2989. Min Range: -0.2989

Max Act: 0.2508. Min Act: -0.0000

Data Index: 15503 (C4 (Web Text))

Max Activating Token Index: 139

Text #4

Max Range: 0.2989. Min Range: -0.2989

Max Act: 0.2197. Min Act: -0.0000

Data Index: 637029 (C4 (Web Text))

Max Activating Token Index: 509

Text #5

Max Range: 0.2989. Min Range: -0.2989

Max Act: 0.1887. Min Act: -0.0000

Data Index: 173264 (C4 (Web Text))

Max Activating Token Index: 303

Text #6

Max Range: 0.2989. Min Range: -0.2989

Max Act: 0.1961. Min Act: -0.0000

Data Index: 337287 (C4 (Web Text))

Max Activating Token Index: 916

Text #7

Max Range: 0.2989. Min Range: -0.2989

Max Act: 0.1905. Min Act: -0.0000

Data Index: 1299462 (C4 (Web Text))

Max Activating Token Index: 872

Text #8

Max Range: 0.2989. Min Range: -0.2989

Max Act: 0.1812. Min Act: -0.0000

Data Index: 1104454 (C4 (Web Text))

Max Activating Token Index: 809

Text #9

Max Range: 0.2989. Min Range: -0.2989

Max Act: 0.2123. Min Act: -0.0000

Data Index: 1358021 (C4 (Web Text))

Max Activating Token Index: 682

Text #10

Max Range: 0.2989. Min Range: -0.2989

Max Act: 0.1973. Min Act: -0.0000

Data Index: 33905 (C4 (Web Text))

Max Activating Token Index: 328

Text #11

Max Range: 0.2989. Min Range: -0.2989

Max Act: 0.1906. Min Act: -0.0000

Data Index: 1346820 (C4 (Web Text))

Max Activating Token Index: 1002

Text #12

Max Range: 0.2989. Min Range: -0.2989

Max Act: 0.2029. Min Act: -0.0000

Data Index: 964505 (C4 (Web Text))

Max Activating Token Index: 71

Text #13

Max Range: 0.2989. Min Range: -0.2989

Max Act: 0.2016. Min Act: -0.0000

Data Index: 1247367 (C4 (Web Text))

Max Activating Token Index: 65

Text #14

Max Range: 0.2989. Min Range: -0.2989

Max Act: 0.1990. Min Act: -0.0000

Data Index: 1583391 (Python Code)

Max Activating Token Index: 395

Text #15

Max Range: 0.2989. Min Range: -0.2989

Max Act: 0.2049. Min Act: -0.0000

Data Index: 746568 (C4 (Web Text))

Max Activating Token Index: 949

Text #16

Max Range: 0.2989. Min Range: -0.2989

Max Act: 0.1938. Min Act: -0.0000

Data Index: 500240 (C4 (Web Text))

Max Activating Token Index: 913

Text #17

Max Range: 0.2989. Min Range: -0.2989

Max Act: 0.1923. Min Act: -0.0000

Data Index: 350686 (C4 (Web Text))

Max Activating Token Index: 939

Text #18

Max Range: 0.2989. Min Range: -0.2989

Max Act: 0.1894. Min Act: -0.0000

Data Index: 384197 (C4 (Web Text))

Max Activating Token Index: 333

Text #19

Max Range: 0.2989. Min Range: -0.2989

Max Act: 0.1972. Min Act: -0.0000

Data Index: 183369 (C4 (Web Text))

Max Activating Token Index: 488