Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1467 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1935. Min Range: -0.1935

Max Act: 0.1935. Min Act: -0.0001

Data Index: 1190291 (C4 (Web Text))

Max Activating Token Index: 571

Text #1

Max Range: 0.1935. Min Range: -0.1935

Max Act: 0.1805. Min Act: -0.0001

Data Index: 587073 (C4 (Web Text))

Max Activating Token Index: 772

Text #2

Max Range: 0.1935. Min Range: -0.1935

Max Act: 0.1749. Min Act: -0.0001

Data Index: 1137059 (C4 (Web Text))

Max Activating Token Index: 213

Text #3

Max Range: 0.1935. Min Range: -0.1935

Max Act: 0.1479. Min Act: -0.0001

Data Index: 1225144 (C4 (Web Text))

Max Activating Token Index: 788

Text #4

Max Range: 0.1935. Min Range: -0.1935

Max Act: 0.1701. Min Act: -0.0001

Data Index: 192386 (C4 (Web Text))

Max Activating Token Index: 777

Text #5

Max Range: 0.1935. Min Range: -0.1935

Max Act: 0.1696. Min Act: -0.0001

Data Index: 154458 (C4 (Web Text))

Max Activating Token Index: 918

Text #6

Max Range: 0.1935. Min Range: -0.1935

Max Act: 0.1466. Min Act: -0.0001

Data Index: 1024496 (C4 (Web Text))

Max Activating Token Index: 717

Text #7

Max Range: 0.1935. Min Range: -0.1935

Max Act: 0.1613. Min Act: -0.0001

Data Index: 733077 (C4 (Web Text))

Max Activating Token Index: 776

Text #8

Max Range: 0.1935. Min Range: -0.1935

Max Act: 0.1721. Min Act: -0.0001

Data Index: 934943 (C4 (Web Text))

Max Activating Token Index: 674

Text #9

Max Range: 0.1935. Min Range: -0.1935

Max Act: 0.1469. Min Act: -0.0001

Data Index: 482284 (C4 (Web Text))

Max Activating Token Index: 581

Text #10

Max Range: 0.1935. Min Range: -0.1935

Max Act: 0.1629. Min Act: -0.0001

Data Index: 746269 (C4 (Web Text))

Max Activating Token Index: 204

Text #11

Max Range: 0.1935. Min Range: -0.1935

Max Act: 0.1546. Min Act: -0.0001

Data Index: 961390 (C4 (Web Text))

Max Activating Token Index: 795

Text #12

Max Range: 0.1935. Min Range: -0.1935

Max Act: 0.1576. Min Act: -0.0001

Data Index: 441133 (C4 (Web Text))

Max Activating Token Index: 890

Text #13

Max Range: 0.1935. Min Range: -0.1935

Max Act: 0.1503. Min Act: -0.0001

Data Index: 569272 (C4 (Web Text))

Max Activating Token Index: 440

Text #14

Max Range: 0.1935. Min Range: -0.1935

Max Act: 0.1508. Min Act: -0.0001

Data Index: 13211 (C4 (Web Text))

Max Activating Token Index: 570

Text #15

Max Range: 0.1935. Min Range: -0.1935

Max Act: 0.1497. Min Act: -0.0001

Data Index: 1389819 (Python Code)

Max Activating Token Index: 864

Text #16

Max Range: 0.1935. Min Range: -0.1935

Max Act: 0.1374. Min Act: -0.0001

Data Index: 999538 (C4 (Web Text))

Max Activating Token Index: 787

Text #17

Max Range: 0.1935. Min Range: -0.1935

Max Act: 0.1417. Min Act: -0.0001

Data Index: 585388 (C4 (Web Text))

Max Activating Token Index: 426

Text #18

Max Range: 0.1935. Min Range: -0.1935

Max Act: 0.1522. Min Act: -0.0001

Data Index: 114779 (C4 (Web Text))

Max Activating Token Index: 728

Text #19

Max Range: 0.1935. Min Range: -0.1935

Max Act: 0.1366. Min Act: -0.0001

Data Index: 1310650 (C4 (Web Text))

Max Activating Token Index: 881