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

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

Neuron 180 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1262. Min Range: -0.1262

Max Act: 0.1223. Min Act: -0.0001

Data Index: 1009681 (C4 (Web Text))

Max Activating Token Index: 174

Text #1

Max Range: 0.1262. Min Range: -0.1262

Max Act: 0.1262. Min Act: -0.0001

Data Index: 58577 (C4 (Web Text))

Max Activating Token Index: 905

Text #2

Max Range: 0.1262. Min Range: -0.1262

Max Act: 0.1109. Min Act: -0.0001

Data Index: 1139513 (C4 (Web Text))

Max Activating Token Index: 15

Text #3

Max Range: 0.1262. Min Range: -0.1262

Max Act: 0.1062. Min Act: -0.0001

Data Index: 945615 (C4 (Web Text))

Max Activating Token Index: 603

Text #4

Max Range: 0.1262. Min Range: -0.1262

Max Act: 0.0946. Min Act: -0.0001

Data Index: 492792 (C4 (Web Text))

Max Activating Token Index: 344

Text #5

Max Range: 0.1262. Min Range: -0.1262

Max Act: 0.0946. Min Act: -0.0001

Data Index: 621815 (C4 (Web Text))

Max Activating Token Index: 680

Text #6

Max Range: 0.1262. Min Range: -0.1262

Max Act: 0.0909. Min Act: -0.0001

Data Index: 233008 (C4 (Web Text))

Max Activating Token Index: 190

Text #7

Max Range: 0.1262. Min Range: -0.1262

Max Act: 0.0898. Min Act: -0.0001

Data Index: 780791 (C4 (Web Text))

Max Activating Token Index: 426

Text #8

Max Range: 0.1262. Min Range: -0.1262

Max Act: 0.0869. Min Act: -0.0001

Data Index: 463824 (C4 (Web Text))

Max Activating Token Index: 520

Text #9

Max Range: 0.1262. Min Range: -0.1262

Max Act: 0.0916. Min Act: -0.0001

Data Index: 616981 (C4 (Web Text))

Max Activating Token Index: 707

Text #10

Max Range: 0.1262. Min Range: -0.1262

Max Act: 0.0917. Min Act: -0.0001

Data Index: 1227041 (C4 (Web Text))

Max Activating Token Index: 355

Text #11

Max Range: 0.1262. Min Range: -0.1262

Max Act: 0.0790. Min Act: -0.0001

Data Index: 1355136 (C4 (Web Text))

Max Activating Token Index: 921

Text #12

Max Range: 0.1262. Min Range: -0.1262

Max Act: 0.0816. Min Act: -0.0001

Data Index: 851442 (C4 (Web Text))

Max Activating Token Index: 760

Text #13

Max Range: 0.1262. Min Range: -0.1262

Max Act: 0.0872. Min Act: -0.0001

Data Index: 1096123 (C4 (Web Text))

Max Activating Token Index: 529

Text #14

Max Range: 0.1262. Min Range: -0.1262

Max Act: 0.0836. Min Act: -0.0001

Data Index: 435854 (C4 (Web Text))

Max Activating Token Index: 134

Text #15

Max Range: 0.1262. Min Range: -0.1262

Max Act: 0.0818. Min Act: -0.0001

Data Index: 530477 (C4 (Web Text))

Max Activating Token Index: 799

Text #16

Max Range: 0.1262. Min Range: -0.1262

Max Act: 0.0849. Min Act: -0.0001

Data Index: 547440 (C4 (Web Text))

Max Activating Token Index: 94

Text #17

Max Range: 0.1262. Min Range: -0.1262

Max Act: 0.0835. Min Act: -0.0001

Data Index: 118880 (C4 (Web Text))

Max Activating Token Index: 495

Text #18

Max Range: 0.1262. Min Range: -0.1262

Max Act: 0.0866. Min Act: -0.0001

Data Index: 1164593 (C4 (Web Text))

Max Activating Token Index: 993

Text #19

Max Range: 0.1262. Min Range: -0.1262

Max Act: 0.0836. Min Act: -0.0001

Data Index: 260841 (C4 (Web Text))

Max Activating Token Index: 987