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

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

Neuron 678 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1839. Min Range: -0.1839

Max Act: 0.1839. Min Act: -0.0000

Data Index: 334930 (C4 (Web Text))

Max Activating Token Index: 500

Text #1

Max Range: 0.1839. Min Range: -0.1839

Max Act: 0.1754. Min Act: -0.0000

Data Index: 591553 (C4 (Web Text))

Max Activating Token Index: 824

Text #2

Max Range: 0.1839. Min Range: -0.1839

Max Act: 0.1556. Min Act: -0.0001

Data Index: 1124823 (C4 (Web Text))

Max Activating Token Index: 187

Text #3

Max Range: 0.1839. Min Range: -0.1839

Max Act: 0.1551. Min Act: -0.0001

Data Index: 1196134 (C4 (Web Text))

Max Activating Token Index: 625

Text #4

Max Range: 0.1839. Min Range: -0.1839

Max Act: 0.1524. Min Act: -0.0000

Data Index: 1299204 (C4 (Web Text))

Max Activating Token Index: 735

Text #5

Max Range: 0.1839. Min Range: -0.1839

Max Act: 0.1497. Min Act: -0.0000

Data Index: 823728 (C4 (Web Text))

Max Activating Token Index: 1004

Text #6

Max Range: 0.1839. Min Range: -0.1839

Max Act: 0.1489. Min Act: -0.0000

Data Index: 294322 (C4 (Web Text))

Max Activating Token Index: 532

Text #7

Max Range: 0.1839. Min Range: -0.1839

Max Act: 0.1486. Min Act: -0.0000

Data Index: 740790 (C4 (Web Text))

Max Activating Token Index: 45

Text #8

Max Range: 0.1839. Min Range: -0.1839

Max Act: 0.1458. Min Act: -0.0000

Data Index: 1216759 (C4 (Web Text))

Max Activating Token Index: 713

Text #9

Max Range: 0.1839. Min Range: -0.1839

Max Act: 0.1448. Min Act: -0.0000

Data Index: 597533 (C4 (Web Text))

Max Activating Token Index: 168

Text #10

Max Range: 0.1839. Min Range: -0.1839

Max Act: 0.1382. Min Act: -0.0001

Data Index: 478354 (C4 (Web Text))

Max Activating Token Index: 638

Text #11

Max Range: 0.1839. Min Range: -0.1839

Max Act: 0.1399. Min Act: -0.0000

Data Index: 1244794 (C4 (Web Text))

Max Activating Token Index: 95

Text #12

Max Range: 0.1839. Min Range: -0.1839

Max Act: 0.1437. Min Act: -0.0001

Data Index: 625839 (C4 (Web Text))

Max Activating Token Index: 293

Text #13

Max Range: 0.1839. Min Range: -0.1839

Max Act: 0.1377. Min Act: -0.0000

Data Index: 13805 (C4 (Web Text))

Max Activating Token Index: 708

Text #14

Max Range: 0.1839. Min Range: -0.1839

Max Act: 0.1413. Min Act: -0.0001

Data Index: 546059 (C4 (Web Text))

Max Activating Token Index: 435

Text #15

Max Range: 0.1839. Min Range: -0.1839

Max Act: 0.1417. Min Act: -0.0000

Data Index: 109275 (C4 (Web Text))

Max Activating Token Index: 509

Text #16

Max Range: 0.1839. Min Range: -0.1839

Max Act: 0.1409. Min Act: -0.0000

Data Index: 218436 (C4 (Web Text))

Max Activating Token Index: 413

Text #17

Max Range: 0.1839. Min Range: -0.1839

Max Act: 0.1403. Min Act: -0.0000

Data Index: 480730 (C4 (Web Text))

Max Activating Token Index: 129

Text #18

Max Range: 0.1839. Min Range: -0.1839

Max Act: 0.1395. Min Act: -0.0000

Data Index: 264168 (C4 (Web Text))

Max Activating Token Index: 193

Text #19

Max Range: 0.1839. Min Range: -0.1839

Max Act: 0.1371. Min Act: -0.0000

Data Index: 383827 (C4 (Web Text))

Max Activating Token Index: 803