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

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

Neuron 232 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: 0.1938. Min Range: -0.1938

Max Act: 0.1862. Min Act: -0.0003

Data Index: 464454 (C4 (Web Text))

Max Activating Token Index: 86

Text #1

Max Range: 0.1938. Min Range: -0.1938

Max Act: 0.1938. Min Act: -0.0003

Data Index: 908582 (C4 (Web Text))

Max Activating Token Index: 996

Text #2

Max Range: 0.1938. Min Range: -0.1938

Max Act: 0.1938. Min Act: -0.0003

Data Index: 662636 (C4 (Web Text))

Max Activating Token Index: 993

Text #3

Max Range: 0.1938. Min Range: -0.1938

Max Act: 0.1926. Min Act: -0.0003

Data Index: 477326 (C4 (Web Text))

Max Activating Token Index: 62

Text #4

Max Range: 0.1938. Min Range: -0.1938

Max Act: 0.1901. Min Act: -0.0003

Data Index: 1003689 (C4 (Web Text))

Max Activating Token Index: 887

Text #5

Max Range: 0.1938. Min Range: -0.1938

Max Act: 0.1892. Min Act: -0.0003

Data Index: 1265227 (C4 (Web Text))

Max Activating Token Index: 742

Text #6

Max Range: 0.1938. Min Range: -0.1938

Max Act: 0.1893. Min Act: -0.0003

Data Index: 1052192 (C4 (Web Text))

Max Activating Token Index: 598

Text #7

Max Range: 0.1938. Min Range: -0.1938

Max Act: 0.1841. Min Act: -0.0003

Data Index: 1084576 (C4 (Web Text))

Max Activating Token Index: 129

Text #8

Max Range: 0.1938. Min Range: -0.1938

Max Act: 0.1651. Min Act: -0.0003

Data Index: 25148 (C4 (Web Text))

Max Activating Token Index: 618

Text #9

Max Range: 0.1938. Min Range: -0.1938

Max Act: 0.1748. Min Act: -0.0003

Data Index: 244377 (C4 (Web Text))

Max Activating Token Index: 809

Text #10

Max Range: 0.1938. Min Range: -0.1938

Max Act: 0.1726. Min Act: -0.0003

Data Index: 1186174 (C4 (Web Text))

Max Activating Token Index: 228

Text #11

Max Range: 0.1938. Min Range: -0.1938

Max Act: 0.1596. Min Act: -0.0003

Data Index: 2364 (C4 (Web Text))

Max Activating Token Index: 552

Text #12

Max Range: 0.1938. Min Range: -0.1938

Max Act: 0.1579. Min Act: -0.0003

Data Index: 475782 (C4 (Web Text))

Max Activating Token Index: 841

Text #13

Max Range: 0.1938. Min Range: -0.1938

Max Act: 0.1644. Min Act: -0.0003

Data Index: 816086 (C4 (Web Text))

Max Activating Token Index: 193

Text #14

Max Range: 0.1938. Min Range: -0.1938

Max Act: 0.1590. Min Act: -0.0003

Data Index: 292766 (C4 (Web Text))

Max Activating Token Index: 368

Text #15

Max Range: 0.1938. Min Range: -0.1938

Max Act: 0.1640. Min Act: -0.0003

Data Index: 125949 (C4 (Web Text))

Max Activating Token Index: 573

Text #16

Max Range: 0.1938. Min Range: -0.1938

Max Act: 0.1752. Min Act: -0.0003

Data Index: 1571971 (Python Code)

Max Activating Token Index: 73

Text #17

Max Range: 0.1938. Min Range: -0.1938

Max Act: 0.1659. Min Act: -0.0003

Data Index: 468854 (C4 (Web Text))

Max Activating Token Index: 661

Text #18

Max Range: 0.1938. Min Range: -0.1938

Max Act: 0.1716. Min Act: -0.0003

Data Index: 1415668 (Python Code)

Max Activating Token Index: 108

Text #19

Max Range: 0.1938. Min Range: -0.1938

Max Act: 0.1704. Min Act: -0.0003

Data Index: 590424 (C4 (Web Text))

Max Activating Token Index: 1010