Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3826 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1946. Min Range: -0.1946

Max Act: 0.1808. Min Act: -0.0001

Data Index: 356518 (C4 (Web Text))

Max Activating Token Index: 740

Text #1

Max Range: 0.1946. Min Range: -0.1946

Max Act: 0.1916. Min Act: -0.0001

Data Index: 755304 (C4 (Web Text))

Max Activating Token Index: 647

Text #2

Max Range: 0.1946. Min Range: -0.1946

Max Act: 0.1801. Min Act: -0.0001

Data Index: 1049385 (C4 (Web Text))

Max Activating Token Index: 764

Text #3

Max Range: 0.1946. Min Range: -0.1946

Max Act: 0.1944. Min Act: -0.0001

Data Index: 187988 (C4 (Web Text))

Max Activating Token Index: 764

Text #4

Max Range: 0.1946. Min Range: -0.1946

Max Act: 0.1946. Min Act: -0.0001

Data Index: 131140 (C4 (Web Text))

Max Activating Token Index: 411

Text #5

Max Range: 0.1946. Min Range: -0.1946

Max Act: 0.1774. Min Act: -0.0001

Data Index: 569692 (C4 (Web Text))

Max Activating Token Index: 480

Text #6

Max Range: 0.1946. Min Range: -0.1946

Max Act: 0.1896. Min Act: -0.0001

Data Index: 1045267 (C4 (Web Text))

Max Activating Token Index: 717

Text #7

Max Range: 0.1946. Min Range: -0.1946

Max Act: 0.1837. Min Act: -0.0001

Data Index: 1335835 (C4 (Web Text))

Max Activating Token Index: 551

Text #8

Max Range: 0.1946. Min Range: -0.1946

Max Act: 0.1885. Min Act: -0.0001

Data Index: 181546 (C4 (Web Text))

Max Activating Token Index: 967

Text #9

Max Range: 0.1946. Min Range: -0.1946

Max Act: 0.1778. Min Act: -0.0001

Data Index: 969790 (C4 (Web Text))

Max Activating Token Index: 604

Text #10

Max Range: 0.1946. Min Range: -0.1946

Max Act: 0.1778. Min Act: -0.0001

Data Index: 430957 (C4 (Web Text))

Max Activating Token Index: 705

Text #11

Max Range: 0.1946. Min Range: -0.1946

Max Act: 0.1798. Min Act: -0.0001

Data Index: 811821 (C4 (Web Text))

Max Activating Token Index: 292

Text #12

Max Range: 0.1946. Min Range: -0.1946

Max Act: 0.1687. Min Act: -0.0001

Data Index: 1114418 (C4 (Web Text))

Max Activating Token Index: 282

Text #13

Max Range: 0.1946. Min Range: -0.1946

Max Act: 0.1648. Min Act: -0.0001

Data Index: 737193 (C4 (Web Text))

Max Activating Token Index: 172

Text #14

Max Range: 0.1946. Min Range: -0.1946

Max Act: 0.1710. Min Act: -0.0001

Data Index: 1261608 (C4 (Web Text))

Max Activating Token Index: 199

Text #15

Max Range: 0.1946. Min Range: -0.1946

Max Act: 0.1770. Min Act: -0.0001

Data Index: 190776 (C4 (Web Text))

Max Activating Token Index: 849

Text #16

Max Range: 0.1946. Min Range: -0.1946

Max Act: 0.1607. Min Act: -0.0001

Data Index: 211133 (C4 (Web Text))

Max Activating Token Index: 616

Text #17

Max Range: 0.1946. Min Range: -0.1946

Max Act: 0.1648. Min Act: -0.0001

Data Index: 1139909 (C4 (Web Text))

Max Activating Token Index: 164

Text #18

Max Range: 0.1946. Min Range: -0.1946

Max Act: 0.1482. Min Act: -0.0001

Data Index: 1188708 (C4 (Web Text))

Max Activating Token Index: 689

Text #19

Max Range: 0.1946. Min Range: -0.1946

Max Act: 0.1469. Min Act: -0.0001

Data Index: 666979 (C4 (Web Text))

Max Activating Token Index: 720