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

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

Neuron 639 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5774. Min Range: -2.5774

Max Act: 2.5774. Min Act: -0.0000

Data Index: 1344865 (C4 (Web Text))

Max Activating Token Index: 842

Text #1

Max Range: 2.5774. Min Range: -2.5774

Max Act: 2.3401. Min Act: -0.0000

Data Index: 590734 (C4 (Web Text))

Max Activating Token Index: 258

Text #2

Max Range: 2.5774. Min Range: -2.5774

Max Act: 2.2237. Min Act: -0.0000

Data Index: 1302265 (C4 (Web Text))

Max Activating Token Index: 358

Text #3

Max Range: 2.5774. Min Range: -2.5774

Max Act: 2.2424. Min Act: -0.0000

Data Index: 638637 (C4 (Web Text))

Max Activating Token Index: 1016

Text #4

Max Range: 2.5774. Min Range: -2.5774

Max Act: 2.2074. Min Act: -0.0000

Data Index: 631346 (C4 (Web Text))

Max Activating Token Index: 695

Text #5

Max Range: 2.5774. Min Range: -2.5774

Max Act: 2.3834. Min Act: -0.0000

Data Index: 372582 (C4 (Web Text))

Max Activating Token Index: 804

Text #6

Max Range: 2.5774. Min Range: -2.5774

Max Act: 2.0762. Min Act: -0.0000

Data Index: 658354 (C4 (Web Text))

Max Activating Token Index: 707

Text #7

Max Range: 2.5774. Min Range: -2.5774

Max Act: 2.0947. Min Act: -0.0000

Data Index: 501982 (C4 (Web Text))

Max Activating Token Index: 167

Text #8

Max Range: 2.5774. Min Range: -2.5774

Max Act: 2.1405. Min Act: -0.0000

Data Index: 97673 (C4 (Web Text))

Max Activating Token Index: 694

Text #9

Max Range: 2.5774. Min Range: -2.5774

Max Act: 2.1211. Min Act: -0.0000

Data Index: 1303661 (C4 (Web Text))

Max Activating Token Index: 927

Text #10

Max Range: 2.5774. Min Range: -2.5774

Max Act: 2.0371. Min Act: -0.0000

Data Index: 1038293 (C4 (Web Text))

Max Activating Token Index: 725

Text #11

Max Range: 2.5774. Min Range: -2.5774

Max Act: 1.8986. Min Act: -0.0000

Data Index: 947053 (C4 (Web Text))

Max Activating Token Index: 985

Text #12

Max Range: 2.5774. Min Range: -2.5774

Max Act: 2.0955. Min Act: -0.0000

Data Index: 303323 (C4 (Web Text))

Max Activating Token Index: 388

Text #13

Max Range: 2.5774. Min Range: -2.5774

Max Act: 2.0750. Min Act: -0.0000

Data Index: 819697 (C4 (Web Text))

Max Activating Token Index: 25

Text #14

Max Range: 2.5774. Min Range: -2.5774

Max Act: 2.1662. Min Act: -0.0000

Data Index: 901486 (C4 (Web Text))

Max Activating Token Index: 493

Text #15

Max Range: 2.5774. Min Range: -2.5774

Max Act: 2.0267. Min Act: -0.0000

Data Index: 918565 (C4 (Web Text))

Max Activating Token Index: 465

Text #16

Max Range: 2.5774. Min Range: -2.5774

Max Act: 1.9158. Min Act: -0.0000

Data Index: 1067428 (C4 (Web Text))

Max Activating Token Index: 67

Text #17

Max Range: 2.5774. Min Range: -2.5774

Max Act: 1.8146. Min Act: -0.0000

Data Index: 1063435 (C4 (Web Text))

Max Activating Token Index: 45

Text #18

Max Range: 2.5774. Min Range: -2.5774

Max Act: 1.8860. Min Act: -0.0000

Data Index: 913149 (C4 (Web Text))

Max Activating Token Index: 693

Text #19

Max Range: 2.5774. Min Range: -2.5774

Max Act: 1.9634. Min Act: -0.0000

Data Index: 1135804 (C4 (Web Text))

Max Activating Token Index: 144