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

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

Neuron 2091 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: 0.8778. Min Range: -0.8778

Max Act: 0.8778. Min Act: -0.0000

Data Index: 290590 (C4 (Web Text))

Max Activating Token Index: 899

Text #1

Max Range: 0.8778. Min Range: -0.8778

Max Act: 0.8460. Min Act: -0.0000

Data Index: 956735 (C4 (Web Text))

Max Activating Token Index: 673

Text #2

Max Range: 0.8778. Min Range: -0.8778

Max Act: 0.7997. Min Act: -0.0000

Data Index: 1161371 (C4 (Web Text))

Max Activating Token Index: 794

Text #3

Max Range: 0.8778. Min Range: -0.8778

Max Act: 0.7242. Min Act: -0.0000

Data Index: 959196 (C4 (Web Text))

Max Activating Token Index: 585

Text #4

Max Range: 0.8778. Min Range: -0.8778

Max Act: 0.7755. Min Act: -0.0000

Data Index: 1263104 (C4 (Web Text))

Max Activating Token Index: 1015

Text #5

Max Range: 0.8778. Min Range: -0.8778

Max Act: 0.6873. Min Act: -0.0000

Data Index: 6830 (C4 (Web Text))

Max Activating Token Index: 63

Text #6

Max Range: 0.8778. Min Range: -0.8778

Max Act: 0.6947. Min Act: -0.0000

Data Index: 796796 (C4 (Web Text))

Max Activating Token Index: 888

Text #7

Max Range: 0.8778. Min Range: -0.8778

Max Act: 0.6767. Min Act: -0.0000

Data Index: 48123 (C4 (Web Text))

Max Activating Token Index: 603

Text #8

Max Range: 0.8778. Min Range: -0.8778

Max Act: 0.6355. Min Act: -0.0000

Data Index: 208066 (C4 (Web Text))

Max Activating Token Index: 172

Text #9

Max Range: 0.8778. Min Range: -0.8778

Max Act: 0.6206. Min Act: -0.0000

Data Index: 234611 (C4 (Web Text))

Max Activating Token Index: 961

Text #10

Max Range: 0.8778. Min Range: -0.8778

Max Act: 0.6404. Min Act: -0.0000

Data Index: 777459 (C4 (Web Text))

Max Activating Token Index: 658

Text #11

Max Range: 0.8778. Min Range: -0.8778

Max Act: 0.6926. Min Act: -0.0000

Data Index: 307442 (C4 (Web Text))

Max Activating Token Index: 1006

Text #12

Max Range: 0.8778. Min Range: -0.8778

Max Act: 0.7407. Min Act: -0.0000

Data Index: 1449548 (Python Code)

Max Activating Token Index: 144

Text #13

Max Range: 0.8778. Min Range: -0.8778

Max Act: 0.6263. Min Act: -0.0000

Data Index: 335664 (C4 (Web Text))

Max Activating Token Index: 974

Text #14

Max Range: 0.8778. Min Range: -0.8778

Max Act: 0.6400. Min Act: -0.0000

Data Index: 1484906 (Python Code)

Max Activating Token Index: 348

Text #15

Max Range: 0.8778. Min Range: -0.8778

Max Act: 0.6710. Min Act: -0.0000

Data Index: 1377258 (Python Code)

Max Activating Token Index: 304

Text #16

Max Range: 0.8778. Min Range: -0.8778

Max Act: 0.6296. Min Act: -0.0000

Data Index: 460727 (C4 (Web Text))

Max Activating Token Index: 388

Text #17

Max Range: 0.8778. Min Range: -0.8778

Max Act: 0.6295. Min Act: -0.0000

Data Index: 1569553 (Python Code)

Max Activating Token Index: 280

Text #18

Max Range: 0.8778. Min Range: -0.8778

Max Act: 0.6133. Min Act: -0.0000

Data Index: 344200 (C4 (Web Text))

Max Activating Token Index: 323

Text #19

Max Range: 0.8778. Min Range: -0.8778

Max Act: 0.6058. Min Act: -0.0000

Data Index: 1486830 (Python Code)

Max Activating Token Index: 951