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

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

Neuron 3174 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1939. Min Range: -0.1939

Max Act: 0.1857. Min Act: -0.0001

Data Index: 1206640 (C4 (Web Text))

Max Activating Token Index: 696

Text #1

Max Range: 0.1939. Min Range: -0.1939

Max Act: 0.1931. Min Act: -0.0001

Data Index: 153478 (C4 (Web Text))

Max Activating Token Index: 575

Text #2

Max Range: 0.1939. Min Range: -0.1939

Max Act: 0.1715. Min Act: -0.0001

Data Index: 1060815 (C4 (Web Text))

Max Activating Token Index: 377

Text #3

Max Range: 0.1939. Min Range: -0.1939

Max Act: 0.1771. Min Act: -0.0001

Data Index: 66285 (C4 (Web Text))

Max Activating Token Index: 548

Text #4

Max Range: 0.1939. Min Range: -0.1939

Max Act: 0.1939. Min Act: -0.0001

Data Index: 1352208 (C4 (Web Text))

Max Activating Token Index: 85

Text #5

Max Range: 0.1939. Min Range: -0.1939

Max Act: 0.1810. Min Act: -0.0001

Data Index: 763329 (C4 (Web Text))

Max Activating Token Index: 417

Text #6

Max Range: 0.1939. Min Range: -0.1939

Max Act: 0.1754. Min Act: -0.0001

Data Index: 830328 (C4 (Web Text))

Max Activating Token Index: 181

Text #7

Max Range: 0.1939. Min Range: -0.1939

Max Act: 0.1816. Min Act: -0.0001

Data Index: 586936 (C4 (Web Text))

Max Activating Token Index: 303

Text #8

Max Range: 0.1939. Min Range: -0.1939

Max Act: 0.1758. Min Act: -0.0001

Data Index: 762849 (C4 (Web Text))

Max Activating Token Index: 764

Text #9

Max Range: 0.1939. Min Range: -0.1939

Max Act: 0.1807. Min Act: -0.0001

Data Index: 1222216 (C4 (Web Text))

Max Activating Token Index: 148

Text #10

Max Range: 0.1939. Min Range: -0.1939

Max Act: 0.1772. Min Act: -0.0001

Data Index: 1173053 (C4 (Web Text))

Max Activating Token Index: 125

Text #11

Max Range: 0.1939. Min Range: -0.1939

Max Act: 0.1921. Min Act: -0.0001

Data Index: 356537 (C4 (Web Text))

Max Activating Token Index: 446

Text #12

Max Range: 0.1939. Min Range: -0.1939

Max Act: 0.1905. Min Act: -0.0001

Data Index: 1076317 (C4 (Web Text))

Max Activating Token Index: 934

Text #13

Max Range: 0.1939. Min Range: -0.1939

Max Act: 0.1775. Min Act: -0.0001

Data Index: 453759 (C4 (Web Text))

Max Activating Token Index: 635

Text #14

Max Range: 0.1939. Min Range: -0.1939

Max Act: 0.1868. Min Act: -0.0001

Data Index: 558209 (C4 (Web Text))

Max Activating Token Index: 414

Text #15

Max Range: 0.1939. Min Range: -0.1939

Max Act: 0.1773. Min Act: -0.0001

Data Index: 399250 (C4 (Web Text))

Max Activating Token Index: 707

Text #16

Max Range: 0.1939. Min Range: -0.1939

Max Act: 0.1831. Min Act: -0.0001

Data Index: 498055 (C4 (Web Text))

Max Activating Token Index: 291

Text #17

Max Range: 0.1939. Min Range: -0.1939

Max Act: 0.1714. Min Act: -0.0001

Data Index: 908732 (C4 (Web Text))

Max Activating Token Index: 888

Text #18

Max Range: 0.1939. Min Range: -0.1939

Max Act: 0.1752. Min Act: -0.0001

Data Index: 1167485 (C4 (Web Text))

Max Activating Token Index: 775

Text #19

Max Range: 0.1939. Min Range: -0.1939

Max Act: 0.1446. Min Act: -0.0001

Data Index: 365860 (C4 (Web Text))

Max Activating Token Index: 334