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

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

Neuron 2316 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1432. Min Range: -1.1432

Max Act: 1.1432. Min Act: -0.0000

Data Index: 1173487 (C4 (Web Text))

Max Activating Token Index: 287

Text #1

Max Range: 1.1432. Min Range: -1.1432

Max Act: 1.0812. Min Act: -0.0000

Data Index: 1010769 (C4 (Web Text))

Max Activating Token Index: 203

Text #2

Max Range: 1.1432. Min Range: -1.1432

Max Act: 0.9189. Min Act: -0.0000

Data Index: 1369994 (Python Code)

Max Activating Token Index: 866

Text #3

Max Range: 1.1432. Min Range: -1.1432

Max Act: 0.9724. Min Act: -0.0000

Data Index: 1389178 (Python Code)

Max Activating Token Index: 505

Text #4

Max Range: 1.1432. Min Range: -1.1432

Max Act: 0.8619. Min Act: -0.0000

Data Index: 552436 (C4 (Web Text))

Max Activating Token Index: 875

Text #5

Max Range: 1.1432. Min Range: -1.1432

Max Act: 0.8514. Min Act: -0.0000

Data Index: 304357 (C4 (Web Text))

Max Activating Token Index: 386

Text #6

Max Range: 1.1432. Min Range: -1.1432

Max Act: 0.8461. Min Act: -0.0000

Data Index: 1621577 (Python Code)

Max Activating Token Index: 106

Text #7

Max Range: 1.1432. Min Range: -1.1432

Max Act: 0.8366. Min Act: -0.0000

Data Index: 1268148 (C4 (Web Text))

Max Activating Token Index: 14

Text #8

Max Range: 1.1432. Min Range: -1.1432

Max Act: 0.8307. Min Act: -0.0000

Data Index: 183405 (C4 (Web Text))

Max Activating Token Index: 382

Text #9

Max Range: 1.1432. Min Range: -1.1432

Max Act: 0.8555. Min Act: -0.0000

Data Index: 692393 (C4 (Web Text))

Max Activating Token Index: 28

Text #10

Max Range: 1.1432. Min Range: -1.1432

Max Act: 0.8441. Min Act: -0.0000

Data Index: 905901 (C4 (Web Text))

Max Activating Token Index: 462

Text #11

Max Range: 1.1432. Min Range: -1.1432

Max Act: 0.8379. Min Act: -0.0000

Data Index: 944840 (C4 (Web Text))

Max Activating Token Index: 693

Text #12

Max Range: 1.1432. Min Range: -1.1432

Max Act: 0.7844. Min Act: -0.0000

Data Index: 46346 (C4 (Web Text))

Max Activating Token Index: 12

Text #13

Max Range: 1.1432. Min Range: -1.1432

Max Act: 0.7521. Min Act: -0.0000

Data Index: 853323 (C4 (Web Text))

Max Activating Token Index: 777

Text #14

Max Range: 1.1432. Min Range: -1.1432

Max Act: 0.7541. Min Act: -0.0000

Data Index: 1180169 (C4 (Web Text))

Max Activating Token Index: 980

Text #15

Max Range: 1.1432. Min Range: -1.1432

Max Act: 0.8007. Min Act: -0.0000

Data Index: 907487 (C4 (Web Text))

Max Activating Token Index: 621

Text #16

Max Range: 1.1432. Min Range: -1.1432

Max Act: 0.8214. Min Act: -0.0000

Data Index: 665333 (C4 (Web Text))

Max Activating Token Index: 862

Text #17

Max Range: 1.1432. Min Range: -1.1432

Max Act: 0.7499. Min Act: -0.0000

Data Index: 946415 (C4 (Web Text))

Max Activating Token Index: 948

Text #18

Max Range: 1.1432. Min Range: -1.1432

Max Act: 0.7416. Min Act: -0.0000

Data Index: 1208450 (C4 (Web Text))

Max Activating Token Index: 567

Text #19

Max Range: 1.1432. Min Range: -1.1432

Max Act: 0.7699. Min Act: -0.0000

Data Index: 1635971 (Python Code)

Max Activating Token Index: 275