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

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

Neuron 2973 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1855. Min Range: -0.1855

Max Act: 0.1855. Min Act: -0.0001

Data Index: 279857 (C4 (Web Text))

Max Activating Token Index: 591

Text #1

Max Range: 0.1855. Min Range: -0.1855

Max Act: 0.1785. Min Act: -0.0001

Data Index: 1182567 (C4 (Web Text))

Max Activating Token Index: 221

Text #2

Max Range: 0.1855. Min Range: -0.1855

Max Act: 0.1700. Min Act: -0.0001

Data Index: 1310981 (C4 (Web Text))

Max Activating Token Index: 32

Text #3

Max Range: 0.1855. Min Range: -0.1855

Max Act: 0.1738. Min Act: -0.0001

Data Index: 946931 (C4 (Web Text))

Max Activating Token Index: 442

Text #4

Max Range: 0.1855. Min Range: -0.1855

Max Act: 0.1635. Min Act: -0.0001

Data Index: 1022310 (C4 (Web Text))

Max Activating Token Index: 101

Text #5

Max Range: 0.1855. Min Range: -0.1855

Max Act: 0.1743. Min Act: -0.0001

Data Index: 1024114 (C4 (Web Text))

Max Activating Token Index: 450

Text #6

Max Range: 0.1855. Min Range: -0.1855

Max Act: 0.1676. Min Act: -0.0001

Data Index: 563308 (C4 (Web Text))

Max Activating Token Index: 177

Text #7

Max Range: 0.1855. Min Range: -0.1855

Max Act: 0.1589. Min Act: -0.0001

Data Index: 636330 (C4 (Web Text))

Max Activating Token Index: 548

Text #8

Max Range: 0.1855. Min Range: -0.1855

Max Act: 0.1638. Min Act: -0.0001

Data Index: 265113 (C4 (Web Text))

Max Activating Token Index: 316

Text #9

Max Range: 0.1855. Min Range: -0.1855

Max Act: 0.1592. Min Act: -0.0001

Data Index: 268866 (C4 (Web Text))

Max Activating Token Index: 603

Text #10

Max Range: 0.1855. Min Range: -0.1855

Max Act: 0.1581. Min Act: -0.0001

Data Index: 390949 (C4 (Web Text))

Max Activating Token Index: 755

Text #11

Max Range: 0.1855. Min Range: -0.1855

Max Act: 0.1548. Min Act: -0.0001

Data Index: 275671 (C4 (Web Text))

Max Activating Token Index: 444

Text #12

Max Range: 0.1855. Min Range: -0.1855

Max Act: 0.1532. Min Act: -0.0001

Data Index: 563803 (C4 (Web Text))

Max Activating Token Index: 403

Text #13

Max Range: 0.1855. Min Range: -0.1855

Max Act: 0.1415. Min Act: -0.0001

Data Index: 239601 (C4 (Web Text))

Max Activating Token Index: 782

Text #14

Max Range: 0.1855. Min Range: -0.1855

Max Act: 0.1461. Min Act: -0.0001

Data Index: 645303 (C4 (Web Text))

Max Activating Token Index: 790

Text #15

Max Range: 0.1855. Min Range: -0.1855

Max Act: 0.1424. Min Act: -0.0001

Data Index: 1355530 (C4 (Web Text))

Max Activating Token Index: 469

Text #16

Max Range: 0.1855. Min Range: -0.1855

Max Act: 0.1413. Min Act: -0.0001

Data Index: 786246 (C4 (Web Text))

Max Activating Token Index: 90

Text #17

Max Range: 0.1855. Min Range: -0.1855

Max Act: 0.1407. Min Act: -0.0001

Data Index: 130948 (C4 (Web Text))

Max Activating Token Index: 343

Text #18

Max Range: 0.1855. Min Range: -0.1855

Max Act: 0.1456. Min Act: -0.0001

Data Index: 361930 (C4 (Web Text))

Max Activating Token Index: 63

Text #19

Max Range: 0.1855. Min Range: -0.1855

Max Act: 0.1351. Min Act: -0.0001

Data Index: 290987 (C4 (Web Text))

Max Activating Token Index: 701