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

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

Neuron 3315 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7619. Min Range: -2.7619

Max Act: 2.7619. Min Act: -0.0000

Data Index: 1623501 (Python Code)

Max Activating Token Index: 271

Text #1

Max Range: 2.7619. Min Range: -2.7619

Max Act: 2.4873. Min Act: -0.0000

Data Index: 1502003 (Python Code)

Max Activating Token Index: 312

Text #2

Max Range: 2.7619. Min Range: -2.7619

Max Act: 2.4398. Min Act: -0.0000

Data Index: 1421616 (Python Code)

Max Activating Token Index: 549

Text #3

Max Range: 2.7619. Min Range: -2.7619

Max Act: 2.3909. Min Act: -0.0000

Data Index: 1645263 (Python Code)

Max Activating Token Index: 502

Text #4

Max Range: 2.7619. Min Range: -2.7619

Max Act: 2.3610. Min Act: -0.0000

Data Index: 1512733 (Python Code)

Max Activating Token Index: 449

Text #5

Max Range: 2.7619. Min Range: -2.7619

Max Act: 2.2076. Min Act: -0.0000

Data Index: 1553651 (Python Code)

Max Activating Token Index: 633

Text #6

Max Range: 2.7619. Min Range: -2.7619

Max Act: 2.0786. Min Act: -0.0000

Data Index: 1639541 (Python Code)

Max Activating Token Index: 399

Text #7

Max Range: 2.7619. Min Range: -2.7619

Max Act: 2.1637. Min Act: -0.0000

Data Index: 1562498 (Python Code)

Max Activating Token Index: 894

Text #8

Max Range: 2.7619. Min Range: -2.7619

Max Act: 2.0505. Min Act: -0.0000

Data Index: 1466269 (Python Code)

Max Activating Token Index: 446

Text #9

Max Range: 2.7619. Min Range: -2.7619

Max Act: 2.1502. Min Act: -0.0000

Data Index: 1399506 (Python Code)

Max Activating Token Index: 515

Text #10

Max Range: 2.7619. Min Range: -2.7619

Max Act: 2.0997. Min Act: -0.0000

Data Index: 1382229 (Python Code)

Max Activating Token Index: 66

Text #11

Max Range: 2.7619. Min Range: -2.7619

Max Act: 1.9910. Min Act: -0.0000

Data Index: 1563980 (Python Code)

Max Activating Token Index: 714

Text #12

Max Range: 2.7619. Min Range: -2.7619

Max Act: 1.9768. Min Act: -0.0000

Data Index: 1455948 (Python Code)

Max Activating Token Index: 605

Text #13

Max Range: 2.7619. Min Range: -2.7619

Max Act: 2.0577. Min Act: -0.0000

Data Index: 1453496 (Python Code)

Max Activating Token Index: 70

Text #14

Max Range: 2.7619. Min Range: -2.7619

Max Act: 2.0357. Min Act: -0.0000

Data Index: 1587767 (Python Code)

Max Activating Token Index: 608

Text #15

Max Range: 2.7619. Min Range: -2.7619

Max Act: 1.9366. Min Act: -0.0000

Data Index: 1389128 (Python Code)

Max Activating Token Index: 994

Text #16

Max Range: 2.7619. Min Range: -2.7619

Max Act: 2.0371. Min Act: -0.0000

Data Index: 1425845 (Python Code)

Max Activating Token Index: 1009

Text #17

Max Range: 2.7619. Min Range: -2.7619

Max Act: 1.9227. Min Act: -0.0000

Data Index: 1379210 (Python Code)

Max Activating Token Index: 522

Text #18

Max Range: 2.7619. Min Range: -2.7619

Max Act: 1.9011. Min Act: -0.0000

Data Index: 1377385 (Python Code)

Max Activating Token Index: 132

Text #19

Max Range: 2.7619. Min Range: -2.7619

Max Act: 2.0007. Min Act: -0.0000

Data Index: 1408072 (Python Code)

Max Activating Token Index: 671