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

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

Neuron 714 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2861. Min Range: -0.2861

Max Act: 0.2861. Min Act: -0.0000

Data Index: 1224922 (C4 (Web Text))

Max Activating Token Index: 142

Text #1

Max Range: 0.2861. Min Range: -0.2861

Max Act: 0.2262. Min Act: -0.0000

Data Index: 52983 (C4 (Web Text))

Max Activating Token Index: 176

Text #2

Max Range: 0.2861. Min Range: -0.2861

Max Act: 0.2261. Min Act: -0.0000

Data Index: 423415 (C4 (Web Text))

Max Activating Token Index: 608

Text #3

Max Range: 0.2861. Min Range: -0.2861

Max Act: 0.2428. Min Act: -0.0000

Data Index: 320722 (C4 (Web Text))

Max Activating Token Index: 463

Text #4

Max Range: 0.2861. Min Range: -0.2861

Max Act: 0.2293. Min Act: -0.0000

Data Index: 610802 (C4 (Web Text))

Max Activating Token Index: 694

Text #5

Max Range: 0.2861. Min Range: -0.2861

Max Act: 0.1924. Min Act: -0.0000

Data Index: 32106 (C4 (Web Text))

Max Activating Token Index: 488

Text #6

Max Range: 0.2861. Min Range: -0.2861

Max Act: 0.2060. Min Act: -0.0000

Data Index: 1097900 (C4 (Web Text))

Max Activating Token Index: 403

Text #7

Max Range: 0.2861. Min Range: -0.2861

Max Act: 0.2042. Min Act: -0.0000

Data Index: 739329 (C4 (Web Text))

Max Activating Token Index: 347

Text #8

Max Range: 0.2861. Min Range: -0.2861

Max Act: 0.1895. Min Act: -0.0000

Data Index: 778808 (C4 (Web Text))

Max Activating Token Index: 139

Text #9

Max Range: 0.2861. Min Range: -0.2861

Max Act: 0.1865. Min Act: -0.0000

Data Index: 1375793 (Python Code)

Max Activating Token Index: 908

Text #10

Max Range: 0.2861. Min Range: -0.2861

Max Act: 0.1887. Min Act: -0.0000

Data Index: 319083 (C4 (Web Text))

Max Activating Token Index: 914

Text #11

Max Range: 0.2861. Min Range: -0.2861

Max Act: 0.1748. Min Act: -0.0000

Data Index: 483156 (C4 (Web Text))

Max Activating Token Index: 728

Text #12

Max Range: 0.2861. Min Range: -0.2861

Max Act: 0.1941. Min Act: -0.0000

Data Index: 417305 (C4 (Web Text))

Max Activating Token Index: 72

Text #13

Max Range: 0.2861. Min Range: -0.2861

Max Act: 0.1860. Min Act: -0.0000

Data Index: 1272150 (C4 (Web Text))

Max Activating Token Index: 924

Text #14

Max Range: 0.2861. Min Range: -0.2861

Max Act: 0.1784. Min Act: -0.0000

Data Index: 730163 (C4 (Web Text))

Max Activating Token Index: 615

Text #15

Max Range: 0.2861. Min Range: -0.2861

Max Act: 0.1830. Min Act: -0.0000

Data Index: 575657 (C4 (Web Text))

Max Activating Token Index: 639

Text #16

Max Range: 0.2861. Min Range: -0.2861

Max Act: 0.1883. Min Act: -0.0000

Data Index: 972677 (C4 (Web Text))

Max Activating Token Index: 451

Text #17

Max Range: 0.2861. Min Range: -0.2861

Max Act: 0.1930. Min Act: -0.0000

Data Index: 348604 (C4 (Web Text))

Max Activating Token Index: 127

Text #18

Max Range: 0.2861. Min Range: -0.2861

Max Act: 0.1738. Min Act: -0.0000

Data Index: 1129330 (C4 (Web Text))

Max Activating Token Index: 105

Text #19

Max Range: 0.2861. Min Range: -0.2861

Max Act: 0.1906. Min Act: -0.0000

Data Index: 237795 (C4 (Web Text))

Max Activating Token Index: 687