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

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

Neuron 2314 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1945. Min Range: -0.1945

Max Act: 0.1945. Min Act: -0.0000

Data Index: 535511 (C4 (Web Text))

Max Activating Token Index: 557

Text #1

Max Range: 0.1945. Min Range: -0.1945

Max Act: 0.1268. Min Act: -0.0000

Data Index: 1220703 (C4 (Web Text))

Max Activating Token Index: 1004

Text #2

Max Range: 0.1945. Min Range: -0.1945

Max Act: 0.1281. Min Act: -0.0000

Data Index: 725613 (C4 (Web Text))

Max Activating Token Index: 946

Text #3

Max Range: 0.1945. Min Range: -0.1945

Max Act: 0.1303. Min Act: -0.0000

Data Index: 1273862 (C4 (Web Text))

Max Activating Token Index: 360

Text #4

Max Range: 0.1945. Min Range: -0.1945

Max Act: 0.1066. Min Act: -0.0000

Data Index: 961751 (C4 (Web Text))

Max Activating Token Index: 178

Text #5

Max Range: 0.1945. Min Range: -0.1945

Max Act: 0.1079. Min Act: -0.0000

Data Index: 1336535 (C4 (Web Text))

Max Activating Token Index: 825

Text #6

Max Range: 0.1945. Min Range: -0.1945

Max Act: 0.1104. Min Act: -0.0000

Data Index: 812194 (C4 (Web Text))

Max Activating Token Index: 862

Text #7

Max Range: 0.1945. Min Range: -0.1945

Max Act: 0.0964. Min Act: -0.0000

Data Index: 1481093 (Python Code)

Max Activating Token Index: 972

Text #8

Max Range: 0.1945. Min Range: -0.1945

Max Act: 0.0975. Min Act: -0.0000

Data Index: 1258867 (C4 (Web Text))

Max Activating Token Index: 350

Text #9

Max Range: 0.1945. Min Range: -0.1945

Max Act: 0.0931. Min Act: -0.0000

Data Index: 726403 (C4 (Web Text))

Max Activating Token Index: 847

Text #10

Max Range: 0.1945. Min Range: -0.1945

Max Act: 0.0996. Min Act: -0.0000

Data Index: 1370714 (Python Code)

Max Activating Token Index: 942

Text #11

Max Range: 0.1945. Min Range: -0.1945

Max Act: 0.0919. Min Act: -0.0000

Data Index: 505081 (C4 (Web Text))

Max Activating Token Index: 162

Text #12

Max Range: 0.1945. Min Range: -0.1945

Max Act: 0.0938. Min Act: -0.0000

Data Index: 542111 (C4 (Web Text))

Max Activating Token Index: 665

Text #13

Max Range: 0.1945. Min Range: -0.1945

Max Act: 0.0927. Min Act: -0.0000

Data Index: 509965 (C4 (Web Text))

Max Activating Token Index: 402

Text #14

Max Range: 0.1945. Min Range: -0.1945

Max Act: 0.0925. Min Act: -0.0000

Data Index: 920792 (C4 (Web Text))

Max Activating Token Index: 545

Text #15

Max Range: 0.1945. Min Range: -0.1945

Max Act: 0.0763. Min Act: -0.0000

Data Index: 945081 (C4 (Web Text))

Max Activating Token Index: 506

Text #16

Max Range: 0.1945. Min Range: -0.1945

Max Act: 0.0986. Min Act: -0.0000

Data Index: 1317186 (C4 (Web Text))

Max Activating Token Index: 418

Text #17

Max Range: 0.1945. Min Range: -0.1945

Max Act: 0.0845. Min Act: -0.0000

Data Index: 254429 (C4 (Web Text))

Max Activating Token Index: 211

Text #18

Max Range: 0.1945. Min Range: -0.1945

Max Act: 0.0788. Min Act: -0.0000

Data Index: 1522785 (Python Code)

Max Activating Token Index: 891

Text #19

Max Range: 0.1945. Min Range: -0.1945

Max Act: 0.0830. Min Act: -0.0000

Data Index: 511446 (C4 (Web Text))

Max Activating Token Index: 319