Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2960 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2574. Min Range: -0.2574

Max Act: 0.2574. Min Act: -0.0003

Data Index: 57760 (C4 (Web Text))

Max Activating Token Index: 959

Text #1

Max Range: 0.2574. Min Range: -0.2574

Max Act: 0.2120. Min Act: -0.0003

Data Index: 738843 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.2574. Min Range: -0.2574

Max Act: 0.2123. Min Act: -0.0003

Data Index: 100311 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.2574. Min Range: -0.2574

Max Act: 0.2049. Min Act: -0.0003

Data Index: 312629 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.2574. Min Range: -0.2574

Max Act: 0.2019. Min Act: -0.0003

Data Index: 476920 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.2574. Min Range: -0.2574

Max Act: 0.1926. Min Act: -0.0003

Data Index: 1519857 (Python Code)

Max Activating Token Index: 989

Text #6

Max Range: 0.2574. Min Range: -0.2574

Max Act: 0.1980. Min Act: -0.0003

Data Index: 187724 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.2574. Min Range: -0.2574

Max Act: 0.1980. Min Act: -0.0003

Data Index: 77866 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.2574. Min Range: -0.2574

Max Act: 0.1925. Min Act: -0.0003

Data Index: 1174402 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.2574. Min Range: -0.2574

Max Act: 0.1819. Min Act: -0.0003

Data Index: 141331 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.2574. Min Range: -0.2574

Max Act: 0.1667. Min Act: -0.0003

Data Index: 671120 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.2574. Min Range: -0.2574

Max Act: 0.1649. Min Act: -0.0003

Data Index: 871037 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.2574. Min Range: -0.2574

Max Act: 0.1791. Min Act: -0.0003

Data Index: 1280182 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.2574. Min Range: -0.2574

Max Act: 0.1648. Min Act: -0.0003

Data Index: 367423 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 0.2574. Min Range: -0.2574

Max Act: 0.1644. Min Act: -0.0003

Data Index: 137702 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.2574. Min Range: -0.2574

Max Act: 0.1629. Min Act: -0.0003

Data Index: 1282324 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.2574. Min Range: -0.2574

Max Act: 0.1567. Min Act: -0.0003

Data Index: 812623 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.2574. Min Range: -0.2574

Max Act: 0.1537. Min Act: -0.0003

Data Index: 609671 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.2574. Min Range: -0.2574

Max Act: 0.1540. Min Act: -0.0003

Data Index: 204311 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.2574. Min Range: -0.2574

Max Act: 0.1561. Min Act: -0.0003

Data Index: 384936 (C4 (Web Text))

Max Activating Token Index: 1023