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

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

Neuron 896 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: 1.2502. Min Range: -1.2502

Max Act: 1.2502. Min Act: -0.0000

Data Index: 1423594 (Python Code)

Max Activating Token Index: 137

Text #1

Max Range: 1.2502. Min Range: -1.2502

Max Act: 1.1444. Min Act: -0.0000

Data Index: 265829 (C4 (Web Text))

Max Activating Token Index: 369

Text #2

Max Range: 1.2502. Min Range: -1.2502

Max Act: 1.1747. Min Act: -0.0000

Data Index: 1465120 (Python Code)

Max Activating Token Index: 439

Text #3

Max Range: 1.2502. Min Range: -1.2502

Max Act: 1.1802. Min Act: -0.0000

Data Index: 1263634 (C4 (Web Text))

Max Activating Token Index: 95

Text #4

Max Range: 1.2502. Min Range: -1.2502

Max Act: 1.1909. Min Act: -0.0000

Data Index: 393101 (C4 (Web Text))

Max Activating Token Index: 653

Text #5

Max Range: 1.2502. Min Range: -1.2502

Max Act: 1.1149. Min Act: -0.0000

Data Index: 8439 (C4 (Web Text))

Max Activating Token Index: 66

Text #6

Max Range: 1.2502. Min Range: -1.2502

Max Act: 1.1066. Min Act: -0.0000

Data Index: 1652296 (Python Code)

Max Activating Token Index: 128

Text #7

Max Range: 1.2502. Min Range: -1.2502

Max Act: 1.1230. Min Act: -0.0000

Data Index: 1272366 (C4 (Web Text))

Max Activating Token Index: 1020

Text #8

Max Range: 1.2502. Min Range: -1.2502

Max Act: 1.1185. Min Act: -0.0000

Data Index: 756641 (C4 (Web Text))

Max Activating Token Index: 196

Text #9

Max Range: 1.2502. Min Range: -1.2502

Max Act: 1.0570. Min Act: -0.0000

Data Index: 230345 (C4 (Web Text))

Max Activating Token Index: 782

Text #10

Max Range: 1.2502. Min Range: -1.2502

Max Act: 1.0968. Min Act: -0.0000

Data Index: 304304 (C4 (Web Text))

Max Activating Token Index: 79

Text #11

Max Range: 1.2502. Min Range: -1.2502

Max Act: 0.9700. Min Act: -0.0000

Data Index: 1614535 (Python Code)

Max Activating Token Index: 448

Text #12

Max Range: 1.2502. Min Range: -1.2502

Max Act: 0.9966. Min Act: -0.0000

Data Index: 1631818 (Python Code)

Max Activating Token Index: 230

Text #13

Max Range: 1.2502. Min Range: -1.2502

Max Act: 1.0499. Min Act: -0.0000

Data Index: 1411506 (Python Code)

Max Activating Token Index: 771

Text #14

Max Range: 1.2502. Min Range: -1.2502

Max Act: 1.1064. Min Act: -0.0000

Data Index: 1565868 (Python Code)

Max Activating Token Index: 212

Text #15

Max Range: 1.2502. Min Range: -1.2502

Max Act: 1.1153. Min Act: -0.0000

Data Index: 719221 (C4 (Web Text))

Max Activating Token Index: 1006

Text #16

Max Range: 1.2502. Min Range: -1.2502

Max Act: 1.0674. Min Act: -0.0000

Data Index: 839871 (C4 (Web Text))

Max Activating Token Index: 749

Text #17

Max Range: 1.2502. Min Range: -1.2502

Max Act: 1.0042. Min Act: -0.0000

Data Index: 1595514 (Python Code)

Max Activating Token Index: 581

Text #18

Max Range: 1.2502. Min Range: -1.2502

Max Act: 1.0521. Min Act: -0.0000

Data Index: 21110 (C4 (Web Text))

Max Activating Token Index: 513

Text #19

Max Range: 1.2502. Min Range: -1.2502

Max Act: 1.0510. Min Act: -0.0000

Data Index: 81464 (C4 (Web Text))

Max Activating Token Index: 676