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

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

Neuron 5031 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6052. Min Range: -0.6052

Max Act: 0.5764. Min Act: -0.0000

Data Index: 1466946 (Python Code)

Max Activating Token Index: 70

Text #1

Max Range: 0.6052. Min Range: -0.6052

Max Act: 0.6052. Min Act: -0.0000

Data Index: 1391631 (Python Code)

Max Activating Token Index: 1008

Text #2

Max Range: 0.6052. Min Range: -0.6052

Max Act: 0.5501. Min Act: -0.0000

Data Index: 1654624 (Python Code)

Max Activating Token Index: 882

Text #3

Max Range: 0.6052. Min Range: -0.6052

Max Act: 0.4750. Min Act: -0.0000

Data Index: 1599066 (Python Code)

Max Activating Token Index: 365

Text #4

Max Range: 0.6052. Min Range: -0.6052

Max Act: 0.4811. Min Act: -0.0000

Data Index: 1404104 (Python Code)

Max Activating Token Index: 119

Text #5

Max Range: 0.6052. Min Range: -0.6052

Max Act: 0.3800. Min Act: -0.0000

Data Index: 1424221 (Python Code)

Max Activating Token Index: 645

Text #6

Max Range: 0.6052. Min Range: -0.6052

Max Act: 0.3574. Min Act: -0.0000

Data Index: 1592183 (Python Code)

Max Activating Token Index: 561

Text #7

Max Range: 0.6052. Min Range: -0.6052

Max Act: 0.3511. Min Act: -0.0000

Data Index: 1491255 (Python Code)

Max Activating Token Index: 424

Text #8

Max Range: 0.6052. Min Range: -0.6052

Max Act: 0.3354. Min Act: -0.0000

Data Index: 1373402 (Python Code)

Max Activating Token Index: 970

Text #9

Max Range: 0.6052. Min Range: -0.6052

Max Act: 0.3431. Min Act: -0.0000

Data Index: 1644076 (Python Code)

Max Activating Token Index: 297

Text #10

Max Range: 0.6052. Min Range: -0.6052

Max Act: 0.3312. Min Act: -0.0000

Data Index: 1062750 (C4 (Web Text))

Max Activating Token Index: 590

Text #11

Max Range: 0.6052. Min Range: -0.6052

Max Act: 0.3249. Min Act: -0.0000

Data Index: 1636420 (Python Code)

Max Activating Token Index: 45

Text #12

Max Range: 0.6052. Min Range: -0.6052

Max Act: 0.3141. Min Act: -0.0000

Data Index: 791895 (C4 (Web Text))

Max Activating Token Index: 195

Text #13

Max Range: 0.6052. Min Range: -0.6052

Max Act: 0.3407. Min Act: -0.0000

Data Index: 1500747 (Python Code)

Max Activating Token Index: 835

Text #14

Max Range: 0.6052. Min Range: -0.6052

Max Act: 0.3062. Min Act: -0.0000

Data Index: 1650088 (Python Code)

Max Activating Token Index: 156

Text #15

Max Range: 0.6052. Min Range: -0.6052

Max Act: 0.2992. Min Act: -0.0000

Data Index: 788812 (C4 (Web Text))

Max Activating Token Index: 817

Text #16

Max Range: 0.6052. Min Range: -0.6052

Max Act: 0.3097. Min Act: -0.0000

Data Index: 428054 (C4 (Web Text))

Max Activating Token Index: 750

Text #17

Max Range: 0.6052. Min Range: -0.6052

Max Act: 0.2759. Min Act: -0.0000

Data Index: 758432 (C4 (Web Text))

Max Activating Token Index: 197

Text #18

Max Range: 0.6052. Min Range: -0.6052

Max Act: 0.2733. Min Act: -0.0000

Data Index: 1477477 (Python Code)

Max Activating Token Index: 914

Text #19

Max Range: 0.6052. Min Range: -0.6052

Max Act: 0.2854. Min Act: -0.0000

Data Index: 474296 (C4 (Web Text))

Max Activating Token Index: 369