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

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

Neuron 4873 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.3246. Min Range: -5.3246

Max Act: 5.3246. Min Act: -0.0001

Data Index: 1570890 (Python Code)

Max Activating Token Index: 21

Text #1

Max Range: 5.3246. Min Range: -5.3246

Max Act: 4.9811. Min Act: -0.0001

Data Index: 1397752 (Python Code)

Max Activating Token Index: 302

Text #2

Max Range: 5.3246. Min Range: -5.3246

Max Act: 2.8113. Min Act: -0.0001

Data Index: 1474072 (Python Code)

Max Activating Token Index: 766

Text #3

Max Range: 5.3246. Min Range: -5.3246

Max Act: 3.2954. Min Act: -0.0001

Data Index: 1565582 (Python Code)

Max Activating Token Index: 90

Text #4

Max Range: 5.3246. Min Range: -5.3246

Max Act: 3.4385. Min Act: -0.0001

Data Index: 1638169 (Python Code)

Max Activating Token Index: 12

Text #5

Max Range: 5.3246. Min Range: -5.3246

Max Act: 3.3511. Min Act: -0.0001

Data Index: 1431445 (Python Code)

Max Activating Token Index: 845

Text #6

Max Range: 5.3246. Min Range: -5.3246

Max Act: 2.7065. Min Act: -0.0001

Data Index: 1608036 (Python Code)

Max Activating Token Index: 319

Text #7

Max Range: 5.3246. Min Range: -5.3246

Max Act: 3.1540. Min Act: -0.0001

Data Index: 1618292 (Python Code)

Max Activating Token Index: 108

Text #8

Max Range: 5.3246. Min Range: -5.3246

Max Act: 3.2826. Min Act: -0.0001

Data Index: 1446727 (Python Code)

Max Activating Token Index: 320

Text #9

Max Range: 5.3246. Min Range: -5.3246

Max Act: 3.0680. Min Act: -0.0001

Data Index: 1612831 (Python Code)

Max Activating Token Index: 53

Text #10

Max Range: 5.3246. Min Range: -5.3246

Max Act: 3.0942. Min Act: -0.0001

Data Index: 1565127 (Python Code)

Max Activating Token Index: 701

Text #11

Max Range: 5.3246. Min Range: -5.3246

Max Act: 3.4732. Min Act: -0.0001

Data Index: 1637287 (Python Code)

Max Activating Token Index: 577

Text #12

Max Range: 5.3246. Min Range: -5.3246

Max Act: 2.8695. Min Act: -0.0001

Data Index: 1535579 (Python Code)

Max Activating Token Index: 423

Text #13

Max Range: 5.3246. Min Range: -5.3246

Max Act: 2.8935. Min Act: -0.0001

Data Index: 1614969 (Python Code)

Max Activating Token Index: 4

Text #14

Max Range: 5.3246. Min Range: -5.3246

Max Act: 2.9676. Min Act: -0.0001

Data Index: 1463186 (Python Code)

Max Activating Token Index: 102

Text #15

Max Range: 5.3246. Min Range: -5.3246

Max Act: 2.7800. Min Act: -0.0001

Data Index: 1443047 (Python Code)

Max Activating Token Index: 426

Text #16

Max Range: 5.3246. Min Range: -5.3246

Max Act: 2.8413. Min Act: -0.0001

Data Index: 1374561 (Python Code)

Max Activating Token Index: 74

Text #17

Max Range: 5.3246. Min Range: -5.3246

Max Act: 2.7982. Min Act: -0.0001

Data Index: 1374795 (Python Code)

Max Activating Token Index: 450

Text #18

Max Range: 5.3246. Min Range: -5.3246

Max Act: 2.7462. Min Act: -0.0001

Data Index: 1581792 (Python Code)

Max Activating Token Index: 57

Text #19

Max Range: 5.3246. Min Range: -5.3246

Max Act: 2.6293. Min Act: -0.0001

Data Index: 1494484 (Python Code)

Max Activating Token Index: 373