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

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

Neuron 265 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2832. Min Range: -2.2832

Max Act: 2.2832. Min Act: -0.0000

Data Index: 1567743 (Python Code)

Max Activating Token Index: 968

Text #1

Max Range: 2.2832. Min Range: -2.2832

Max Act: 1.9242. Min Act: -0.0000

Data Index: 1499640 (Python Code)

Max Activating Token Index: 212

Text #2

Max Range: 2.2832. Min Range: -2.2832

Max Act: 1.7386. Min Act: -0.0000

Data Index: 1625961 (Python Code)

Max Activating Token Index: 177

Text #3

Max Range: 2.2832. Min Range: -2.2832

Max Act: 1.6498. Min Act: -0.0000

Data Index: 1595947 (Python Code)

Max Activating Token Index: 437

Text #4

Max Range: 2.2832. Min Range: -2.2832

Max Act: 1.0470. Min Act: -0.0000

Data Index: 1639141 (Python Code)

Max Activating Token Index: 537

Text #5

Max Range: 2.2832. Min Range: -2.2832

Max Act: 0.8971. Min Act: -0.0000

Data Index: 1456078 (Python Code)

Max Activating Token Index: 722

Text #6

Max Range: 2.2832. Min Range: -2.2832

Max Act: 0.9270. Min Act: -0.0000

Data Index: 1643880 (Python Code)

Max Activating Token Index: 779

Text #7

Max Range: 2.2832. Min Range: -2.2832

Max Act: 0.8544. Min Act: -0.0000

Data Index: 1425786 (Python Code)

Max Activating Token Index: 385

Text #8

Max Range: 2.2832. Min Range: -2.2832

Max Act: 0.7393. Min Act: -0.0000

Data Index: 1426111 (Python Code)

Max Activating Token Index: 264

Text #9

Max Range: 2.2832. Min Range: -2.2832

Max Act: 0.8291. Min Act: -0.0000

Data Index: 1418028 (Python Code)

Max Activating Token Index: 87

Text #10

Max Range: 2.2832. Min Range: -2.2832

Max Act: 0.7598. Min Act: -0.0000

Data Index: 1577283 (Python Code)

Max Activating Token Index: 616

Text #11

Max Range: 2.2832. Min Range: -2.2832

Max Act: 0.6699. Min Act: -0.0000

Data Index: 1624763 (Python Code)

Max Activating Token Index: 1022

Text #12

Max Range: 2.2832. Min Range: -2.2832

Max Act: 0.7381. Min Act: -0.0000

Data Index: 1399367 (Python Code)

Max Activating Token Index: 224

Text #13

Max Range: 2.2832. Min Range: -2.2832

Max Act: 0.6941. Min Act: -0.0000

Data Index: 1640991 (Python Code)

Max Activating Token Index: 936

Text #14

Max Range: 2.2832. Min Range: -2.2832

Max Act: 0.7243. Min Act: -0.0000

Data Index: 1582624 (Python Code)

Max Activating Token Index: 141

Text #15

Max Range: 2.2832. Min Range: -2.2832

Max Act: 0.6669. Min Act: -0.0000

Data Index: 1416719 (Python Code)

Max Activating Token Index: 724

Text #16

Max Range: 2.2832. Min Range: -2.2832

Max Act: 0.5901. Min Act: -0.0000

Data Index: 1457371 (Python Code)

Max Activating Token Index: 694

Text #17

Max Range: 2.2832. Min Range: -2.2832

Max Act: 0.7353. Min Act: -0.0000

Data Index: 1437280 (Python Code)

Max Activating Token Index: 265

Text #18

Max Range: 2.2832. Min Range: -2.2832

Max Act: 0.6664. Min Act: -0.0000

Data Index: 1431557 (Python Code)

Max Activating Token Index: 745

Text #19

Max Range: 2.2832. Min Range: -2.2832

Max Act: 0.6973. Min Act: -0.0000

Data Index: 1519393 (Python Code)

Max Activating Token Index: 834