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

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

Neuron 2763 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: 0.6795. Min Range: -0.6795

Max Act: 0.6209. Min Act: -0.0000

Data Index: 1283875 (C4 (Web Text))

Max Activating Token Index: 43

Text #1

Max Range: 0.6795. Min Range: -0.6795

Max Act: 0.6429. Min Act: -0.0000

Data Index: 1265697 (C4 (Web Text))

Max Activating Token Index: 73

Text #2

Max Range: 0.6795. Min Range: -0.6795

Max Act: 0.6367. Min Act: -0.0000

Data Index: 475793 (C4 (Web Text))

Max Activating Token Index: 829

Text #3

Max Range: 0.6795. Min Range: -0.6795

Max Act: 0.6795. Min Act: -0.0000

Data Index: 1254093 (C4 (Web Text))

Max Activating Token Index: 288

Text #4

Max Range: 0.6795. Min Range: -0.6795

Max Act: 0.5915. Min Act: -0.0000

Data Index: 614180 (C4 (Web Text))

Max Activating Token Index: 194

Text #5

Max Range: 0.6795. Min Range: -0.6795

Max Act: 0.5915. Min Act: -0.0000

Data Index: 561210 (C4 (Web Text))

Max Activating Token Index: 563

Text #6

Max Range: 0.6795. Min Range: -0.6795

Max Act: 0.6073. Min Act: -0.0000

Data Index: 21137 (C4 (Web Text))

Max Activating Token Index: 635

Text #7

Max Range: 0.6795. Min Range: -0.6795

Max Act: 0.6108. Min Act: -0.0000

Data Index: 848769 (C4 (Web Text))

Max Activating Token Index: 654

Text #8

Max Range: 0.6795. Min Range: -0.6795

Max Act: 0.5547. Min Act: -0.0000

Data Index: 662825 (C4 (Web Text))

Max Activating Token Index: 607

Text #9

Max Range: 0.6795. Min Range: -0.6795

Max Act: 0.5900. Min Act: -0.0000

Data Index: 842075 (C4 (Web Text))

Max Activating Token Index: 800

Text #10

Max Range: 0.6795. Min Range: -0.6795

Max Act: 0.5612. Min Act: -0.0000

Data Index: 203140 (C4 (Web Text))

Max Activating Token Index: 764

Text #11

Max Range: 0.6795. Min Range: -0.6795

Max Act: 0.5066. Min Act: -0.0000

Data Index: 748101 (C4 (Web Text))

Max Activating Token Index: 753

Text #12

Max Range: 0.6795. Min Range: -0.6795

Max Act: 0.5271. Min Act: -0.0000

Data Index: 335400 (C4 (Web Text))

Max Activating Token Index: 332

Text #13

Max Range: 0.6795. Min Range: -0.6795

Max Act: 0.5231. Min Act: -0.0000

Data Index: 1325965 (C4 (Web Text))

Max Activating Token Index: 283

Text #14

Max Range: 0.6795. Min Range: -0.6795

Max Act: 0.5355. Min Act: -0.0000

Data Index: 210493 (C4 (Web Text))

Max Activating Token Index: 93

Text #15

Max Range: 0.6795. Min Range: -0.6795

Max Act: 0.5032. Min Act: -0.0000

Data Index: 859926 (C4 (Web Text))

Max Activating Token Index: 788

Text #16

Max Range: 0.6795. Min Range: -0.6795

Max Act: 0.4782. Min Act: -0.0000

Data Index: 876206 (C4 (Web Text))

Max Activating Token Index: 979

Text #17

Max Range: 0.6795. Min Range: -0.6795

Max Act: 0.4992. Min Act: -0.0000

Data Index: 819191 (C4 (Web Text))

Max Activating Token Index: 649

Text #18

Max Range: 0.6795. Min Range: -0.6795

Max Act: 0.4914. Min Act: -0.0000

Data Index: 454292 (C4 (Web Text))

Max Activating Token Index: 372

Text #19

Max Range: 0.6795. Min Range: -0.6795

Max Act: 0.4942. Min Act: -0.0000

Data Index: 1058827 (C4 (Web Text))

Max Activating Token Index: 531