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

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

Neuron 2322 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8346. Min Range: -0.8346

Max Act: 0.8346. Min Act: -0.0001

Data Index: 1616477 (Python Code)

Max Activating Token Index: 645

Text #1

Max Range: 0.8346. Min Range: -0.8346

Max Act: 0.7810. Min Act: -0.0001

Data Index: 1475165 (Python Code)

Max Activating Token Index: 950

Text #2

Max Range: 0.8346. Min Range: -0.8346

Max Act: 0.8101. Min Act: -0.0001

Data Index: 1560693 (Python Code)

Max Activating Token Index: 583

Text #3

Max Range: 0.8346. Min Range: -0.8346

Max Act: 0.7885. Min Act: -0.0001

Data Index: 1396822 (Python Code)

Max Activating Token Index: 996

Text #4

Max Range: 0.8346. Min Range: -0.8346

Max Act: 0.7203. Min Act: -0.0001

Data Index: 1388813 (Python Code)

Max Activating Token Index: 914

Text #5

Max Range: 0.8346. Min Range: -0.8346

Max Act: 0.7059. Min Act: -0.0001

Data Index: 1627063 (Python Code)

Max Activating Token Index: 265

Text #6

Max Range: 0.8346. Min Range: -0.8346

Max Act: 0.6648. Min Act: -0.0001

Data Index: 1464212 (Python Code)

Max Activating Token Index: 124

Text #7

Max Range: 0.8346. Min Range: -0.8346

Max Act: 0.6876. Min Act: -0.0001

Data Index: 1377415 (Python Code)

Max Activating Token Index: 415

Text #8

Max Range: 0.8346. Min Range: -0.8346

Max Act: 0.6866. Min Act: -0.0001

Data Index: 1510697 (Python Code)

Max Activating Token Index: 25

Text #9

Max Range: 0.8346. Min Range: -0.8346

Max Act: 0.6770. Min Act: -0.0001

Data Index: 1536808 (Python Code)

Max Activating Token Index: 993

Text #10

Max Range: 0.8346. Min Range: -0.8346

Max Act: 0.6193. Min Act: -0.0001

Data Index: 1496595 (Python Code)

Max Activating Token Index: 620

Text #11

Max Range: 0.8346. Min Range: -0.8346

Max Act: 0.6351. Min Act: -0.0001

Data Index: 1460437 (Python Code)

Max Activating Token Index: 821

Text #12

Max Range: 0.8346. Min Range: -0.8346

Max Act: 0.6133. Min Act: -0.0001

Data Index: 1424401 (Python Code)

Max Activating Token Index: 779

Text #13

Max Range: 0.8346. Min Range: -0.8346

Max Act: 0.6774. Min Act: -0.0001

Data Index: 1418398 (Python Code)

Max Activating Token Index: 223

Text #14

Max Range: 0.8346. Min Range: -0.8346

Max Act: 0.6458. Min Act: -0.0001

Data Index: 1456448 (Python Code)

Max Activating Token Index: 540

Text #15

Max Range: 0.8346. Min Range: -0.8346

Max Act: 0.6414. Min Act: -0.0001

Data Index: 1632852 (Python Code)

Max Activating Token Index: 444

Text #16

Max Range: 0.8346. Min Range: -0.8346

Max Act: 0.6447. Min Act: -0.0001

Data Index: 1445170 (Python Code)

Max Activating Token Index: 104

Text #17

Max Range: 0.8346. Min Range: -0.8346

Max Act: 0.6275. Min Act: -0.0001

Data Index: 1390015 (Python Code)

Max Activating Token Index: 504

Text #18

Max Range: 0.8346. Min Range: -0.8346

Max Act: 0.6331. Min Act: -0.0001

Data Index: 1473703 (Python Code)

Max Activating Token Index: 274

Text #19

Max Range: 0.8346. Min Range: -0.8346

Max Act: 0.6050. Min Act: -0.0001

Data Index: 1382164 (Python Code)

Max Activating Token Index: 78