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

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

Neuron 2628 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5514. Min Range: -2.5514

Max Act: 2.5514. Min Act: -0.0000

Data Index: 834917 (C4 (Web Text))

Max Activating Token Index: 171

Text #1

Max Range: 2.5514. Min Range: -2.5514

Max Act: 2.1127. Min Act: -0.0000

Data Index: 721634 (C4 (Web Text))

Max Activating Token Index: 434

Text #2

Max Range: 2.5514. Min Range: -2.5514

Max Act: 2.0058. Min Act: -0.0000

Data Index: 585525 (C4 (Web Text))

Max Activating Token Index: 84

Text #3

Max Range: 2.5514. Min Range: -2.5514

Max Act: 1.8346. Min Act: -0.0000

Data Index: 273807 (C4 (Web Text))

Max Activating Token Index: 716

Text #4

Max Range: 2.5514. Min Range: -2.5514

Max Act: 1.8197. Min Act: -0.0001

Data Index: 288575 (C4 (Web Text))

Max Activating Token Index: 361

Text #5

Max Range: 2.5514. Min Range: -2.5514

Max Act: 1.7832. Min Act: -0.0000

Data Index: 1185101 (C4 (Web Text))

Max Activating Token Index: 307

Text #6

Max Range: 2.5514. Min Range: -2.5514

Max Act: 1.4778. Min Act: -0.0000

Data Index: 564934 (C4 (Web Text))

Max Activating Token Index: 330

Text #7

Max Range: 2.5514. Min Range: -2.5514

Max Act: 1.7425. Min Act: -0.0000

Data Index: 692937 (C4 (Web Text))

Max Activating Token Index: 561

Text #8

Max Range: 2.5514. Min Range: -2.5514

Max Act: 1.6251. Min Act: -0.0001

Data Index: 932539 (C4 (Web Text))

Max Activating Token Index: 888

Text #9

Max Range: 2.5514. Min Range: -2.5514

Max Act: 1.4758. Min Act: -0.0000

Data Index: 824094 (C4 (Web Text))

Max Activating Token Index: 822

Text #10

Max Range: 2.5514. Min Range: -2.5514

Max Act: 1.4696. Min Act: -0.0000

Data Index: 1449497 (Python Code)

Max Activating Token Index: 768

Text #11

Max Range: 2.5514. Min Range: -2.5514

Max Act: 1.4543. Min Act: -0.0000

Data Index: 1434864 (Python Code)

Max Activating Token Index: 163

Text #12

Max Range: 2.5514. Min Range: -2.5514

Max Act: 1.4852. Min Act: -0.0000

Data Index: 1537769 (Python Code)

Max Activating Token Index: 423

Text #13

Max Range: 2.5514. Min Range: -2.5514

Max Act: 1.3924. Min Act: -0.0001

Data Index: 965699 (C4 (Web Text))

Max Activating Token Index: 657

Text #14

Max Range: 2.5514. Min Range: -2.5514

Max Act: 1.3993. Min Act: -0.0000

Data Index: 223873 (C4 (Web Text))

Max Activating Token Index: 513

Text #15

Max Range: 2.5514. Min Range: -2.5514

Max Act: 1.3559. Min Act: -0.0000

Data Index: 1386782 (Python Code)

Max Activating Token Index: 805

Text #16

Max Range: 2.5514. Min Range: -2.5514

Max Act: 1.4936. Min Act: -0.0000

Data Index: 1215364 (C4 (Web Text))

Max Activating Token Index: 849

Text #17

Max Range: 2.5514. Min Range: -2.5514

Max Act: 1.4796. Min Act: -0.0000

Data Index: 470872 (C4 (Web Text))

Max Activating Token Index: 461

Text #18

Max Range: 2.5514. Min Range: -2.5514

Max Act: 1.2945. Min Act: -0.0000

Data Index: 874219 (C4 (Web Text))

Max Activating Token Index: 433

Text #19

Max Range: 2.5514. Min Range: -2.5514

Max Act: 1.3926. Min Act: -0.0000

Data Index: 1358097 (C4 (Web Text))

Max Activating Token Index: 480