Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 864 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.1946. Min Range: -2.1946

Max Act: 1.7229. Min Act: -0.0000

Data Index: 41698 (C4 (Web Text))

Max Activating Token Index: 149

Text #1

Max Range: 2.1946. Min Range: -2.1946

Max Act: 2.1946. Min Act: -0.0000

Data Index: 1335365 (C4 (Web Text))

Max Activating Token Index: 27

Text #2

Max Range: 2.1946. Min Range: -2.1946

Max Act: 2.1629. Min Act: -0.0000

Data Index: 1368870 (Python Code)

Max Activating Token Index: 973

Text #3

Max Range: 2.1946. Min Range: -2.1946

Max Act: 2.0639. Min Act: -0.0000

Data Index: 1471367 (Python Code)

Max Activating Token Index: 973

Text #4

Max Range: 2.1946. Min Range: -2.1946

Max Act: 1.8290. Min Act: -0.0001

Data Index: 1622642 (Python Code)

Max Activating Token Index: 816

Text #5

Max Range: 2.1946. Min Range: -2.1946

Max Act: 1.9119. Min Act: -0.0000

Data Index: 1580603 (Python Code)

Max Activating Token Index: 233

Text #6

Max Range: 2.1946. Min Range: -2.1946

Max Act: 1.7527. Min Act: -0.0000

Data Index: 826895 (C4 (Web Text))

Max Activating Token Index: 800

Text #7

Max Range: 2.1946. Min Range: -2.1946

Max Act: 1.9900. Min Act: -0.0000

Data Index: 140827 (C4 (Web Text))

Max Activating Token Index: 468

Text #8

Max Range: 2.1946. Min Range: -2.1946

Max Act: 1.9778. Min Act: -0.0000

Data Index: 1498902 (Python Code)

Max Activating Token Index: 972

Text #9

Max Range: 2.1946. Min Range: -2.1946

Max Act: 1.9579. Min Act: -0.0001

Data Index: 1477070 (Python Code)

Max Activating Token Index: 995

Text #10

Max Range: 2.1946. Min Range: -2.1946

Max Act: 1.9560. Min Act: -0.0000

Data Index: 1506475 (Python Code)

Max Activating Token Index: 932

Text #11

Max Range: 2.1946. Min Range: -2.1946

Max Act: 2.0620. Min Act: -0.0000

Data Index: 1632766 (Python Code)

Max Activating Token Index: 958

Text #12

Max Range: 2.1946. Min Range: -2.1946

Max Act: 1.9347. Min Act: -0.0001

Data Index: 1530501 (Python Code)

Max Activating Token Index: 890

Text #13

Max Range: 2.1946. Min Range: -2.1946

Max Act: 1.8325. Min Act: -0.0001

Data Index: 1428617 (Python Code)

Max Activating Token Index: 285

Text #14

Max Range: 2.1946. Min Range: -2.1946

Max Act: 1.9363. Min Act: -0.0000

Data Index: 1634544 (Python Code)

Max Activating Token Index: 963

Text #15

Max Range: 2.1946. Min Range: -2.1946

Max Act: 1.7076. Min Act: -0.0000

Data Index: 1458721 (Python Code)

Max Activating Token Index: 877

Text #16

Max Range: 2.1946. Min Range: -2.1946

Max Act: 1.8672. Min Act: -0.0000

Data Index: 1619207 (Python Code)

Max Activating Token Index: 716

Text #17

Max Range: 2.1946. Min Range: -2.1946

Max Act: 1.9867. Min Act: -0.0001

Data Index: 1529634 (Python Code)

Max Activating Token Index: 799

Text #18

Max Range: 2.1946. Min Range: -2.1946

Max Act: 1.8751. Min Act: -0.0000

Data Index: 1635518 (Python Code)

Max Activating Token Index: 718

Text #19

Max Range: 2.1946. Min Range: -2.1946

Max Act: 1.6127. Min Act: -0.0000

Data Index: 1632593 (Python Code)

Max Activating Token Index: 948