Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1997 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.1741. Min Range: -2.1741

Max Act: 2.1530. Min Act: -0.0000

Data Index: 1349540 (C4 (Web Text))

Max Activating Token Index: 936

Text #1

Max Range: 2.1741. Min Range: -2.1741

Max Act: 2.0326. Min Act: -0.0000

Data Index: 1349899 (C4 (Web Text))

Max Activating Token Index: 519

Text #2

Max Range: 2.1741. Min Range: -2.1741

Max Act: 1.9270. Min Act: -0.0000

Data Index: 1168400 (C4 (Web Text))

Max Activating Token Index: 489

Text #3

Max Range: 2.1741. Min Range: -2.1741

Max Act: 1.8364. Min Act: -0.0000

Data Index: 1171006 (C4 (Web Text))

Max Activating Token Index: 85

Text #4

Max Range: 2.1741. Min Range: -2.1741

Max Act: 1.7597. Min Act: -0.0000

Data Index: 763704 (C4 (Web Text))

Max Activating Token Index: 217

Text #5

Max Range: 2.1741. Min Range: -2.1741

Max Act: 1.5807. Min Act: -0.0001

Data Index: 1081617 (C4 (Web Text))

Max Activating Token Index: 290

Text #6

Max Range: 2.1741. Min Range: -2.1741

Max Act: 2.1741. Min Act: -0.0000

Data Index: 1126174 (C4 (Web Text))

Max Activating Token Index: 765

Text #7

Max Range: 2.1741. Min Range: -2.1741

Max Act: 1.9572. Min Act: -0.0000

Data Index: 1356288 (C4 (Web Text))

Max Activating Token Index: 268

Text #8

Max Range: 2.1741. Min Range: -2.1741

Max Act: 1.6150. Min Act: -0.0000

Data Index: 963945 (C4 (Web Text))

Max Activating Token Index: 399

Text #9

Max Range: 2.1741. Min Range: -2.1741

Max Act: 1.8460. Min Act: -0.0000

Data Index: 634388 (C4 (Web Text))

Max Activating Token Index: 695

Text #10

Max Range: 2.1741. Min Range: -2.1741

Max Act: 1.7627. Min Act: -0.0000

Data Index: 971499 (C4 (Web Text))

Max Activating Token Index: 51

Text #11

Max Range: 2.1741. Min Range: -2.1741

Max Act: 2.1357. Min Act: -0.0000

Data Index: 601931 (C4 (Web Text))

Max Activating Token Index: 159

Text #12

Max Range: 2.1741. Min Range: -2.1741

Max Act: 1.7419. Min Act: -0.0000

Data Index: 113210 (C4 (Web Text))

Max Activating Token Index: 7

Text #13

Max Range: 2.1741. Min Range: -2.1741

Max Act: 1.8348. Min Act: -0.0001

Data Index: 968334 (C4 (Web Text))

Max Activating Token Index: 10

Text #14

Max Range: 2.1741. Min Range: -2.1741

Max Act: 1.7342. Min Act: -0.0000

Data Index: 337361 (C4 (Web Text))

Max Activating Token Index: 182

Text #15

Max Range: 2.1741. Min Range: -2.1741

Max Act: 1.7969. Min Act: -0.0001

Data Index: 1176134 (C4 (Web Text))

Max Activating Token Index: 685

Text #16

Max Range: 2.1741. Min Range: -2.1741

Max Act: 1.7636. Min Act: -0.0000

Data Index: 980937 (C4 (Web Text))

Max Activating Token Index: 186

Text #17

Max Range: 2.1741. Min Range: -2.1741

Max Act: 1.7485. Min Act: -0.0000

Data Index: 36113 (C4 (Web Text))

Max Activating Token Index: 693

Text #18

Max Range: 2.1741. Min Range: -2.1741

Max Act: 1.6398. Min Act: -0.0000

Data Index: 77412 (C4 (Web Text))

Max Activating Token Index: 87

Text #19

Max Range: 2.1741. Min Range: -2.1741

Max Act: 1.7352. Min Act: -0.0001

Data Index: 390366 (C4 (Web Text))

Max Activating Token Index: 19