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

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

Neuron 3504 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2882. Min Range: -0.2882

Max Act: 0.2882. Min Act: -0.0000

Data Index: 1183237 (C4 (Web Text))

Max Activating Token Index: 711

Text #1

Max Range: 0.2882. Min Range: -0.2882

Max Act: 0.2252. Min Act: -0.0000

Data Index: 1337091 (C4 (Web Text))

Max Activating Token Index: 953

Text #2

Max Range: 0.2882. Min Range: -0.2882

Max Act: 0.2459. Min Act: -0.0000

Data Index: 819481 (C4 (Web Text))

Max Activating Token Index: 90

Text #3

Max Range: 0.2882. Min Range: -0.2882

Max Act: 0.2172. Min Act: -0.0000

Data Index: 5203 (C4 (Web Text))

Max Activating Token Index: 801

Text #4

Max Range: 0.2882. Min Range: -0.2882

Max Act: 0.2288. Min Act: -0.0000

Data Index: 1168830 (C4 (Web Text))

Max Activating Token Index: 462

Text #5

Max Range: 0.2882. Min Range: -0.2882

Max Act: 0.2110. Min Act: -0.0000

Data Index: 43437 (C4 (Web Text))

Max Activating Token Index: 341

Text #6

Max Range: 0.2882. Min Range: -0.2882

Max Act: 0.1813. Min Act: -0.0000

Data Index: 467692 (C4 (Web Text))

Max Activating Token Index: 213

Text #7

Max Range: 0.2882. Min Range: -0.2882

Max Act: 0.1907. Min Act: -0.0000

Data Index: 408670 (C4 (Web Text))

Max Activating Token Index: 585

Text #8

Max Range: 0.2882. Min Range: -0.2882

Max Act: 0.1901. Min Act: -0.0000

Data Index: 516474 (C4 (Web Text))

Max Activating Token Index: 630

Text #9

Max Range: 0.2882. Min Range: -0.2882

Max Act: 0.1865. Min Act: -0.0000

Data Index: 170766 (C4 (Web Text))

Max Activating Token Index: 249

Text #10

Max Range: 0.2882. Min Range: -0.2882

Max Act: 0.1905. Min Act: -0.0000

Data Index: 1005147 (C4 (Web Text))

Max Activating Token Index: 577

Text #11

Max Range: 0.2882. Min Range: -0.2882

Max Act: 0.1919. Min Act: -0.0000

Data Index: 300046 (C4 (Web Text))

Max Activating Token Index: 914

Text #12

Max Range: 0.2882. Min Range: -0.2882

Max Act: 0.1872. Min Act: -0.0000

Data Index: 1103736 (C4 (Web Text))

Max Activating Token Index: 925

Text #13

Max Range: 0.2882. Min Range: -0.2882

Max Act: 0.1887. Min Act: -0.0000

Data Index: 1353795 (C4 (Web Text))

Max Activating Token Index: 630

Text #14

Max Range: 0.2882. Min Range: -0.2882

Max Act: 0.1926. Min Act: -0.0000

Data Index: 979681 (C4 (Web Text))

Max Activating Token Index: 601

Text #15

Max Range: 0.2882. Min Range: -0.2882

Max Act: 0.1968. Min Act: -0.0000

Data Index: 958437 (C4 (Web Text))

Max Activating Token Index: 556

Text #16

Max Range: 0.2882. Min Range: -0.2882

Max Act: 0.1992. Min Act: -0.0000

Data Index: 774879 (C4 (Web Text))

Max Activating Token Index: 435

Text #17

Max Range: 0.2882. Min Range: -0.2882

Max Act: 0.1986. Min Act: -0.0000

Data Index: 1271958 (C4 (Web Text))

Max Activating Token Index: 404

Text #18

Max Range: 0.2882. Min Range: -0.2882

Max Act: 0.1955. Min Act: -0.0000

Data Index: 1532849 (Python Code)

Max Activating Token Index: 769

Text #19

Max Range: 0.2882. Min Range: -0.2882

Max Act: 0.1924. Min Act: -0.0000

Data Index: 540379 (C4 (Web Text))

Max Activating Token Index: 722