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

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

Neuron 4300 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3550. Min Range: -0.3550

Max Act: 0.3550. Min Act: -0.0000

Data Index: 1553244 (Python Code)

Max Activating Token Index: 683

Text #1

Max Range: 0.3550. Min Range: -0.3550

Max Act: 0.3353. Min Act: -0.0000

Data Index: 1458689 (Python Code)

Max Activating Token Index: 880

Text #2

Max Range: 0.3550. Min Range: -0.3550

Max Act: 0.3293. Min Act: -0.0000

Data Index: 1570733 (Python Code)

Max Activating Token Index: 880

Text #3

Max Range: 0.3550. Min Range: -0.3550

Max Act: 0.2601. Min Act: -0.0000

Data Index: 1524124 (Python Code)

Max Activating Token Index: 515

Text #4

Max Range: 0.3550. Min Range: -0.3550

Max Act: 0.2749. Min Act: -0.0000

Data Index: 1461315 (Python Code)

Max Activating Token Index: 946

Text #5

Max Range: 0.3550. Min Range: -0.3550

Max Act: 0.2481. Min Act: -0.0000

Data Index: 1528140 (Python Code)

Max Activating Token Index: 844

Text #6

Max Range: 0.3550. Min Range: -0.3550

Max Act: 0.2679. Min Act: -0.0000

Data Index: 1364232 (Python Code)

Max Activating Token Index: 738

Text #7

Max Range: 0.3550. Min Range: -0.3550

Max Act: 0.2657. Min Act: -0.0000

Data Index: 1569417 (Python Code)

Max Activating Token Index: 504

Text #8

Max Range: 0.3550. Min Range: -0.3550

Max Act: 0.2680. Min Act: -0.0000

Data Index: 1566625 (Python Code)

Max Activating Token Index: 294

Text #9

Max Range: 0.3550. Min Range: -0.3550

Max Act: 0.2592. Min Act: -0.0000

Data Index: 1606746 (Python Code)

Max Activating Token Index: 271

Text #10

Max Range: 0.3550. Min Range: -0.3550

Max Act: 0.2347. Min Act: -0.0000

Data Index: 1545548 (Python Code)

Max Activating Token Index: 1021

Text #11

Max Range: 0.3550. Min Range: -0.3550

Max Act: 0.2616. Min Act: -0.0000

Data Index: 1418830 (Python Code)

Max Activating Token Index: 499

Text #12

Max Range: 0.3550. Min Range: -0.3550

Max Act: 0.2559. Min Act: -0.0000

Data Index: 1452611 (Python Code)

Max Activating Token Index: 277

Text #13

Max Range: 0.3550. Min Range: -0.3550

Max Act: 0.2459. Min Act: -0.0000

Data Index: 1650120 (Python Code)

Max Activating Token Index: 663

Text #14

Max Range: 0.3550. Min Range: -0.3550

Max Act: 0.2439. Min Act: -0.0000

Data Index: 1410226 (Python Code)

Max Activating Token Index: 309

Text #15

Max Range: 0.3550. Min Range: -0.3550

Max Act: 0.2608. Min Act: -0.0000

Data Index: 1496015 (Python Code)

Max Activating Token Index: 903

Text #16

Max Range: 0.3550. Min Range: -0.3550

Max Act: 0.2418. Min Act: -0.0000

Data Index: 886314 (C4 (Web Text))

Max Activating Token Index: 629

Text #17

Max Range: 0.3550. Min Range: -0.3550

Max Act: 0.2422. Min Act: -0.0000

Data Index: 1540443 (Python Code)

Max Activating Token Index: 500

Text #18

Max Range: 0.3550. Min Range: -0.3550

Max Act: 0.2312. Min Act: -0.0000

Data Index: 293817 (C4 (Web Text))

Max Activating Token Index: 392

Text #19

Max Range: 0.3550. Min Range: -0.3550

Max Act: 0.2280. Min Act: -0.0000

Data Index: 442956 (C4 (Web Text))

Max Activating Token Index: 102