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

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

Neuron 2508 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: 0.1686. Min Range: -0.1686

Max Act: 0.1686. Min Act: -0.0001

Data Index: 828169 (C4 (Web Text))

Max Activating Token Index: 691

Text #1

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1679. Min Act: -0.0001

Data Index: 1176013 (C4 (Web Text))

Max Activating Token Index: 471

Text #2

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1617. Min Act: -0.0001

Data Index: 404106 (C4 (Web Text))

Max Activating Token Index: 128

Text #3

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1570. Min Act: -0.0001

Data Index: 312074 (C4 (Web Text))

Max Activating Token Index: 104

Text #4

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1567. Min Act: -0.0001

Data Index: 3804 (C4 (Web Text))

Max Activating Token Index: 831

Text #5

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1635. Min Act: -0.0001

Data Index: 1114182 (C4 (Web Text))

Max Activating Token Index: 700

Text #6

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1545. Min Act: -0.0001

Data Index: 179879 (C4 (Web Text))

Max Activating Token Index: 833

Text #7

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1539. Min Act: -0.0001

Data Index: 91384 (C4 (Web Text))

Max Activating Token Index: 245

Text #8

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1635. Min Act: -0.0001

Data Index: 570625 (C4 (Web Text))

Max Activating Token Index: 62

Text #9

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1492. Min Act: -0.0001

Data Index: 265007 (C4 (Web Text))

Max Activating Token Index: 918

Text #10

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1493. Min Act: -0.0001

Data Index: 1036615 (C4 (Web Text))

Max Activating Token Index: 393

Text #11

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1489. Min Act: -0.0001

Data Index: 777003 (C4 (Web Text))

Max Activating Token Index: 1014

Text #12

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1425. Min Act: -0.0001

Data Index: 131672 (C4 (Web Text))

Max Activating Token Index: 845

Text #13

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1454. Min Act: -0.0001

Data Index: 1109381 (C4 (Web Text))

Max Activating Token Index: 837

Text #14

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1419. Min Act: -0.0001

Data Index: 1306112 (C4 (Web Text))

Max Activating Token Index: 774

Text #15

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1466. Min Act: -0.0001

Data Index: 17254 (C4 (Web Text))

Max Activating Token Index: 677

Text #16

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1443. Min Act: -0.0001

Data Index: 38728 (C4 (Web Text))

Max Activating Token Index: 756

Text #17

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1440. Min Act: -0.0001

Data Index: 293409 (C4 (Web Text))

Max Activating Token Index: 716

Text #18

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1341. Min Act: -0.0001

Data Index: 311506 (C4 (Web Text))

Max Activating Token Index: 725

Text #19

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1380. Min Act: -0.0001

Data Index: 915197 (C4 (Web Text))

Max Activating Token Index: 289