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

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

Neuron 4745 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: 0.8624. Min Range: -0.8624

Max Act: 0.7129. Min Act: -0.0000

Data Index: 1554253 (Python Code)

Max Activating Token Index: 955

Text #1

Max Range: 0.8624. Min Range: -0.8624

Max Act: 0.7961. Min Act: -0.0000

Data Index: 1492287 (Python Code)

Max Activating Token Index: 287

Text #2

Max Range: 0.8624. Min Range: -0.8624

Max Act: 0.6530. Min Act: -0.0000

Data Index: 1525868 (Python Code)

Max Activating Token Index: 652

Text #3

Max Range: 0.8624. Min Range: -0.8624

Max Act: 0.6448. Min Act: -0.0000

Data Index: 585892 (C4 (Web Text))

Max Activating Token Index: 645

Text #4

Max Range: 0.8624. Min Range: -0.8624

Max Act: 0.8624. Min Act: -0.0000

Data Index: 997744 (C4 (Web Text))

Max Activating Token Index: 32

Text #5

Max Range: 0.8624. Min Range: -0.8624

Max Act: 0.7430. Min Act: -0.0000

Data Index: 1514368 (Python Code)

Max Activating Token Index: 702

Text #6

Max Range: 0.8624. Min Range: -0.8624

Max Act: 0.7260. Min Act: -0.0000

Data Index: 930972 (C4 (Web Text))

Max Activating Token Index: 13

Text #7

Max Range: 0.8624. Min Range: -0.8624

Max Act: 0.6426. Min Act: -0.0000

Data Index: 1498307 (Python Code)

Max Activating Token Index: 851

Text #8

Max Range: 0.8624. Min Range: -0.8624

Max Act: 0.7070. Min Act: -0.0000

Data Index: 1049178 (C4 (Web Text))

Max Activating Token Index: 921

Text #9

Max Range: 0.8624. Min Range: -0.8624

Max Act: 0.6517. Min Act: -0.0000

Data Index: 1560419 (Python Code)

Max Activating Token Index: 879

Text #10

Max Range: 0.8624. Min Range: -0.8624

Max Act: 0.8133. Min Act: -0.0000

Data Index: 1620523 (Python Code)

Max Activating Token Index: 430

Text #11

Max Range: 0.8624. Min Range: -0.8624

Max Act: 0.6622. Min Act: -0.0000

Data Index: 1603970 (Python Code)

Max Activating Token Index: 591

Text #12

Max Range: 0.8624. Min Range: -0.8624

Max Act: 0.6592. Min Act: -0.0000

Data Index: 1495053 (Python Code)

Max Activating Token Index: 629

Text #13

Max Range: 0.8624. Min Range: -0.8624

Max Act: 0.7247. Min Act: -0.0000

Data Index: 1493343 (Python Code)

Max Activating Token Index: 581

Text #14

Max Range: 0.8624. Min Range: -0.8624

Max Act: 0.5841. Min Act: -0.0000

Data Index: 1643932 (Python Code)

Max Activating Token Index: 203

Text #15

Max Range: 0.8624. Min Range: -0.8624

Max Act: 0.7261. Min Act: -0.0000

Data Index: 1312559 (C4 (Web Text))

Max Activating Token Index: 278

Text #16

Max Range: 0.8624. Min Range: -0.8624

Max Act: 0.7068. Min Act: -0.0000

Data Index: 1628350 (Python Code)

Max Activating Token Index: 858

Text #17

Max Range: 0.8624. Min Range: -0.8624

Max Act: 0.6698. Min Act: -0.0000

Data Index: 185177 (C4 (Web Text))

Max Activating Token Index: 12

Text #18

Max Range: 0.8624. Min Range: -0.8624

Max Act: 0.6103. Min Act: -0.0000

Data Index: 545867 (C4 (Web Text))

Max Activating Token Index: 379

Text #19

Max Range: 0.8624. Min Range: -0.8624

Max Act: 0.6105. Min Act: -0.0000

Data Index: 1595249 (Python Code)

Max Activating Token Index: 651