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

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

Neuron 2496 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.2495. Min Range: -5.2495

Max Act: 5.2495. Min Act: -0.0001

Data Index: 1543089 (Python Code)

Max Activating Token Index: 335

Text #1

Max Range: 5.2495. Min Range: -5.2495

Max Act: 5.1691. Min Act: -0.0001

Data Index: 1461287 (Python Code)

Max Activating Token Index: 622

Text #2

Max Range: 5.2495. Min Range: -5.2495

Max Act: 5.1152. Min Act: -0.0001

Data Index: 1625856 (Python Code)

Max Activating Token Index: 173

Text #3

Max Range: 5.2495. Min Range: -5.2495

Max Act: 5.2193. Min Act: -0.0001

Data Index: 1491302 (Python Code)

Max Activating Token Index: 399

Text #4

Max Range: 5.2495. Min Range: -5.2495

Max Act: 4.6747. Min Act: -0.0001

Data Index: 1499044 (Python Code)

Max Activating Token Index: 278

Text #5

Max Range: 5.2495. Min Range: -5.2495

Max Act: 5.0954. Min Act: -0.0001

Data Index: 1638369 (Python Code)

Max Activating Token Index: 551

Text #6

Max Range: 5.2495. Min Range: -5.2495

Max Act: 4.7176. Min Act: -0.0001

Data Index: 1467624 (Python Code)

Max Activating Token Index: 877

Text #7

Max Range: 5.2495. Min Range: -5.2495

Max Act: 5.2349. Min Act: -0.0001

Data Index: 1512108 (Python Code)

Max Activating Token Index: 398

Text #8

Max Range: 5.2495. Min Range: -5.2495

Max Act: 5.0108. Min Act: -0.0001

Data Index: 1592601 (Python Code)

Max Activating Token Index: 320

Text #9

Max Range: 5.2495. Min Range: -5.2495

Max Act: 4.6292. Min Act: -0.0001

Data Index: 1456928 (Python Code)

Max Activating Token Index: 108

Text #10

Max Range: 5.2495. Min Range: -5.2495

Max Act: 4.5857. Min Act: -0.0001

Data Index: 1585988 (Python Code)

Max Activating Token Index: 827

Text #11

Max Range: 5.2495. Min Range: -5.2495

Max Act: 4.7393. Min Act: -0.0001

Data Index: 1417731 (Python Code)

Max Activating Token Index: 202

Text #12

Max Range: 5.2495. Min Range: -5.2495

Max Act: 4.5600. Min Act: -0.0001

Data Index: 1614448 (Python Code)

Max Activating Token Index: 220

Text #13

Max Range: 5.2495. Min Range: -5.2495

Max Act: 4.8817. Min Act: -0.0001

Data Index: 1502840 (Python Code)

Max Activating Token Index: 180

Text #14

Max Range: 5.2495. Min Range: -5.2495

Max Act: 4.6637. Min Act: -0.0001

Data Index: 1559428 (Python Code)

Max Activating Token Index: 660

Text #15

Max Range: 5.2495. Min Range: -5.2495

Max Act: 4.6564. Min Act: -0.0001

Data Index: 1591268 (Python Code)

Max Activating Token Index: 44

Text #16

Max Range: 5.2495. Min Range: -5.2495

Max Act: 4.5388. Min Act: -0.0001

Data Index: 1531608 (Python Code)

Max Activating Token Index: 209

Text #17

Max Range: 5.2495. Min Range: -5.2495

Max Act: 4.5520. Min Act: -0.0001

Data Index: 1511493 (Python Code)

Max Activating Token Index: 203

Text #18

Max Range: 5.2495. Min Range: -5.2495

Max Act: 4.6686. Min Act: -0.0001

Data Index: 1588935 (Python Code)

Max Activating Token Index: 715

Text #19

Max Range: 5.2495. Min Range: -5.2495

Max Act: 4.6832. Min Act: -0.0001

Data Index: 1592724 (Python Code)

Max Activating Token Index: 203