Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 46 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1921. Min Range: -0.1921

Max Act: 0.1890. Min Act: -0.0001

Data Index: 1192036 (C4 (Web Text))

Max Activating Token Index: 18

Text #1

Max Range: 0.1921. Min Range: -0.1921

Max Act: 0.1921. Min Act: -0.0001

Data Index: 1164624 (C4 (Web Text))

Max Activating Token Index: 443

Text #2

Max Range: 0.1921. Min Range: -0.1921

Max Act: 0.1634. Min Act: -0.0001

Data Index: 636385 (C4 (Web Text))

Max Activating Token Index: 10

Text #3

Max Range: 0.1921. Min Range: -0.1921

Max Act: 0.1642. Min Act: -0.0001

Data Index: 626777 (C4 (Web Text))

Max Activating Token Index: 46

Text #4

Max Range: 0.1921. Min Range: -0.1921

Max Act: 0.1587. Min Act: -0.0001

Data Index: 1274252 (C4 (Web Text))

Max Activating Token Index: 845

Text #5

Max Range: 0.1921. Min Range: -0.1921

Max Act: 0.1647. Min Act: -0.0001

Data Index: 932043 (C4 (Web Text))

Max Activating Token Index: 405

Text #6

Max Range: 0.1921. Min Range: -0.1921

Max Act: 0.1466. Min Act: -0.0001

Data Index: 938465 (C4 (Web Text))

Max Activating Token Index: 207

Text #7

Max Range: 0.1921. Min Range: -0.1921

Max Act: 0.1484. Min Act: -0.0001

Data Index: 1232167 (C4 (Web Text))

Max Activating Token Index: 169

Text #8

Max Range: 0.1921. Min Range: -0.1921

Max Act: 0.1526. Min Act: -0.0001

Data Index: 389699 (C4 (Web Text))

Max Activating Token Index: 851

Text #9

Max Range: 0.1921. Min Range: -0.1921

Max Act: 0.1457. Min Act: -0.0001

Data Index: 48109 (C4 (Web Text))

Max Activating Token Index: 539

Text #10

Max Range: 0.1921. Min Range: -0.1921

Max Act: 0.1425. Min Act: -0.0001

Data Index: 1310709 (C4 (Web Text))

Max Activating Token Index: 219

Text #11

Max Range: 0.1921. Min Range: -0.1921

Max Act: 0.1396. Min Act: -0.0001

Data Index: 1026072 (C4 (Web Text))

Max Activating Token Index: 504

Text #12

Max Range: 0.1921. Min Range: -0.1921

Max Act: 0.1387. Min Act: -0.0001

Data Index: 498133 (C4 (Web Text))

Max Activating Token Index: 453

Text #13

Max Range: 0.1921. Min Range: -0.1921

Max Act: 0.1303. Min Act: -0.0001

Data Index: 919232 (C4 (Web Text))

Max Activating Token Index: 910

Text #14

Max Range: 0.1921. Min Range: -0.1921

Max Act: 0.1371. Min Act: -0.0001

Data Index: 76585 (C4 (Web Text))

Max Activating Token Index: 708

Text #15

Max Range: 0.1921. Min Range: -0.1921

Max Act: 0.1326. Min Act: -0.0001

Data Index: 352418 (C4 (Web Text))

Max Activating Token Index: 390

Text #16

Max Range: 0.1921. Min Range: -0.1921

Max Act: 0.1283. Min Act: -0.0001

Data Index: 1595 (C4 (Web Text))

Max Activating Token Index: 67

Text #17

Max Range: 0.1921. Min Range: -0.1921

Max Act: 0.1363. Min Act: -0.0001

Data Index: 796188 (C4 (Web Text))

Max Activating Token Index: 531

Text #18

Max Range: 0.1921. Min Range: -0.1921

Max Act: 0.1305. Min Act: -0.0001

Data Index: 892450 (C4 (Web Text))

Max Activating Token Index: 543

Text #19

Max Range: 0.1921. Min Range: -0.1921

Max Act: 0.1226. Min Act: -0.0001

Data Index: 395350 (C4 (Web Text))

Max Activating Token Index: 837