Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1166 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.2518. Min Range: -0.2518

Max Act: 0.2518. Min Act: -0.0003

Data Index: 1014597 (C4 (Web Text))

Max Activating Token Index: 745

Text #1

Max Range: 0.2518. Min Range: -0.2518

Max Act: 0.2040. Min Act: -0.0003

Data Index: 561876 (C4 (Web Text))

Max Activating Token Index: 904

Text #2

Max Range: 0.2518. Min Range: -0.2518

Max Act: 0.2103. Min Act: -0.0002

Data Index: 1066075 (C4 (Web Text))

Max Activating Token Index: 771

Text #3

Max Range: 0.2518. Min Range: -0.2518

Max Act: 0.1979. Min Act: -0.0003

Data Index: 96532 (C4 (Web Text))

Max Activating Token Index: 996

Text #4

Max Range: 0.2518. Min Range: -0.2518

Max Act: 0.1854. Min Act: -0.0003

Data Index: 360366 (C4 (Web Text))

Max Activating Token Index: 947

Text #5

Max Range: 0.2518. Min Range: -0.2518

Max Act: 0.1976. Min Act: -0.0003

Data Index: 640040 (C4 (Web Text))

Max Activating Token Index: 408

Text #6

Max Range: 0.2518. Min Range: -0.2518

Max Act: 0.1822. Min Act: -0.0003

Data Index: 1216050 (C4 (Web Text))

Max Activating Token Index: 822

Text #7

Max Range: 0.2518. Min Range: -0.2518

Max Act: 0.1958. Min Act: -0.0003

Data Index: 539854 (C4 (Web Text))

Max Activating Token Index: 235

Text #8

Max Range: 0.2518. Min Range: -0.2518

Max Act: 0.1887. Min Act: -0.0003

Data Index: 891197 (C4 (Web Text))

Max Activating Token Index: 493

Text #9

Max Range: 0.2518. Min Range: -0.2518

Max Act: 0.1957. Min Act: -0.0003

Data Index: 1000074 (C4 (Web Text))

Max Activating Token Index: 240

Text #10

Max Range: 0.2518. Min Range: -0.2518

Max Act: 0.1948. Min Act: -0.0003

Data Index: 775207 (C4 (Web Text))

Max Activating Token Index: 41

Text #11

Max Range: 0.2518. Min Range: -0.2518

Max Act: 0.1873. Min Act: -0.0003

Data Index: 1010013 (C4 (Web Text))

Max Activating Token Index: 369

Text #12

Max Range: 0.2518. Min Range: -0.2518

Max Act: 0.1861. Min Act: -0.0003

Data Index: 92915 (C4 (Web Text))

Max Activating Token Index: 524

Text #13

Max Range: 0.2518. Min Range: -0.2518

Max Act: 0.2062. Min Act: -0.0003

Data Index: 624685 (C4 (Web Text))

Max Activating Token Index: 102

Text #14

Max Range: 0.2518. Min Range: -0.2518

Max Act: 0.1767. Min Act: -0.0003

Data Index: 988478 (C4 (Web Text))

Max Activating Token Index: 872

Text #15

Max Range: 0.2518. Min Range: -0.2518

Max Act: 0.1881. Min Act: -0.0003

Data Index: 68306 (C4 (Web Text))

Max Activating Token Index: 779

Text #16

Max Range: 0.2518. Min Range: -0.2518

Max Act: 0.1884. Min Act: -0.0003

Data Index: 128261 (C4 (Web Text))

Max Activating Token Index: 371

Text #17

Max Range: 0.2518. Min Range: -0.2518

Max Act: 0.1699. Min Act: -0.0003

Data Index: 42954 (C4 (Web Text))

Max Activating Token Index: 1003

Text #18

Max Range: 0.2518. Min Range: -0.2518

Max Act: 0.1860. Min Act: -0.0003

Data Index: 447417 (C4 (Web Text))

Max Activating Token Index: 89

Text #19

Max Range: 0.2518. Min Range: -0.2518

Max Act: 0.1933. Min Act: -0.0003

Data Index: 702175 (C4 (Web Text))

Max Activating Token Index: 1005