Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 4047 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.1468. Min Range: -1.1468

Max Act: 1.1468. Min Act: -0.0003

Data Index: 1625911 (Python Code)

Max Activating Token Index: 946

Text #1

Max Range: 1.1468. Min Range: -1.1468

Max Act: 1.0224. Min Act: -0.0003

Data Index: 1595875 (Python Code)

Max Activating Token Index: 495

Text #2

Max Range: 1.1468. Min Range: -1.1468

Max Act: 0.9866. Min Act: -0.0003

Data Index: 1072500 (C4 (Web Text))

Max Activating Token Index: 656

Text #3

Max Range: 1.1468. Min Range: -1.1468

Max Act: 1.0470. Min Act: -0.0004

Data Index: 1299032 (C4 (Web Text))

Max Activating Token Index: 614

Text #4

Max Range: 1.1468. Min Range: -1.1468

Max Act: 1.0187. Min Act: -0.0003

Data Index: 799639 (C4 (Web Text))

Max Activating Token Index: 544

Text #5

Max Range: 1.1468. Min Range: -1.1468

Max Act: 1.0152. Min Act: -0.0003

Data Index: 769912 (C4 (Web Text))

Max Activating Token Index: 520

Text #6

Max Range: 1.1468. Min Range: -1.1468

Max Act: 1.0673. Min Act: -0.0003

Data Index: 1563918 (Python Code)

Max Activating Token Index: 396

Text #7

Max Range: 1.1468. Min Range: -1.1468

Max Act: 0.9080. Min Act: -0.0003

Data Index: 29677 (C4 (Web Text))

Max Activating Token Index: 530

Text #8

Max Range: 1.1468. Min Range: -1.1468

Max Act: 0.9429. Min Act: -0.0003

Data Index: 1506155 (Python Code)

Max Activating Token Index: 682

Text #9

Max Range: 1.1468. Min Range: -1.1468

Max Act: 0.9422. Min Act: -0.0003

Data Index: 846497 (C4 (Web Text))

Max Activating Token Index: 363

Text #10

Max Range: 1.1468. Min Range: -1.1468

Max Act: 0.9095. Min Act: -0.0003

Data Index: 1462842 (Python Code)

Max Activating Token Index: 685

Text #11

Max Range: 1.1468. Min Range: -1.1468

Max Act: 0.9923. Min Act: -0.0003

Data Index: 273038 (C4 (Web Text))

Max Activating Token Index: 360

Text #12

Max Range: 1.1468. Min Range: -1.1468

Max Act: 1.0223. Min Act: -0.0003

Data Index: 323567 (C4 (Web Text))

Max Activating Token Index: 445

Text #13

Max Range: 1.1468. Min Range: -1.1468

Max Act: 0.9312. Min Act: -0.0003

Data Index: 1028919 (C4 (Web Text))

Max Activating Token Index: 514

Text #14

Max Range: 1.1468. Min Range: -1.1468

Max Act: 1.0207. Min Act: -0.0003

Data Index: 905806 (C4 (Web Text))

Max Activating Token Index: 701

Text #15

Max Range: 1.1468. Min Range: -1.1468

Max Act: 0.9357. Min Act: -0.0003

Data Index: 1117638 (C4 (Web Text))

Max Activating Token Index: 646

Text #16

Max Range: 1.1468. Min Range: -1.1468

Max Act: 1.0739. Min Act: -0.0003

Data Index: 1365128 (Python Code)

Max Activating Token Index: 389

Text #17

Max Range: 1.1468. Min Range: -1.1468

Max Act: 1.0110. Min Act: -0.0003

Data Index: 694299 (C4 (Web Text))

Max Activating Token Index: 403

Text #18

Max Range: 1.1468. Min Range: -1.1468

Max Act: 0.9768. Min Act: -0.0003

Data Index: 979864 (C4 (Web Text))

Max Activating Token Index: 525

Text #19

Max Range: 1.1468. Min Range: -1.1468

Max Act: 1.0737. Min Act: -0.0003

Data Index: 982497 (C4 (Web Text))

Max Activating Token Index: 519