Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3899 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.4441. Min Range: -1.4441

Max Act: 1.4441. Min Act: -0.0001

Data Index: 1464244 (Python Code)

Max Activating Token Index: 282

Text #1

Max Range: 1.4441. Min Range: -1.4441

Max Act: 1.3543. Min Act: -0.0001

Data Index: 150776 (C4 (Web Text))

Max Activating Token Index: 632

Text #2

Max Range: 1.4441. Min Range: -1.4441

Max Act: 1.3330. Min Act: -0.0001

Data Index: 1597484 (Python Code)

Max Activating Token Index: 397

Text #3

Max Range: 1.4441. Min Range: -1.4441

Max Act: 1.1963. Min Act: -0.0001

Data Index: 1614937 (Python Code)

Max Activating Token Index: 547

Text #4

Max Range: 1.4441. Min Range: -1.4441

Max Act: 1.2303. Min Act: -0.0001

Data Index: 1558742 (Python Code)

Max Activating Token Index: 937

Text #5

Max Range: 1.4441. Min Range: -1.4441

Max Act: 1.2741. Min Act: -0.0001

Data Index: 1562410 (Python Code)

Max Activating Token Index: 678

Text #6

Max Range: 1.4441. Min Range: -1.4441

Max Act: 1.2063. Min Act: -0.0001

Data Index: 1483101 (Python Code)

Max Activating Token Index: 528

Text #7

Max Range: 1.4441. Min Range: -1.4441

Max Act: 1.1872. Min Act: -0.0001

Data Index: 1622057 (Python Code)

Max Activating Token Index: 246

Text #8

Max Range: 1.4441. Min Range: -1.4441

Max Act: 1.1494. Min Act: -0.0001

Data Index: 1454196 (Python Code)

Max Activating Token Index: 902

Text #9

Max Range: 1.4441. Min Range: -1.4441

Max Act: 1.1640. Min Act: -0.0001

Data Index: 1454770 (Python Code)

Max Activating Token Index: 523

Text #10

Max Range: 1.4441. Min Range: -1.4441

Max Act: 1.2408. Min Act: -0.0001

Data Index: 1484608 (Python Code)

Max Activating Token Index: 51

Text #11

Max Range: 1.4441. Min Range: -1.4441

Max Act: 1.3117. Min Act: -0.0001

Data Index: 1565949 (Python Code)

Max Activating Token Index: 68

Text #12

Max Range: 1.4441. Min Range: -1.4441

Max Act: 1.2328. Min Act: -0.0001

Data Index: 1550025 (Python Code)

Max Activating Token Index: 6

Text #13

Max Range: 1.4441. Min Range: -1.4441

Max Act: 1.2026. Min Act: -0.0001

Data Index: 1606706 (Python Code)

Max Activating Token Index: 591

Text #14

Max Range: 1.4441. Min Range: -1.4441

Max Act: 1.1531. Min Act: -0.0001

Data Index: 1427293 (Python Code)

Max Activating Token Index: 706

Text #15

Max Range: 1.4441. Min Range: -1.4441

Max Act: 1.1699. Min Act: -0.0001

Data Index: 1459295 (Python Code)

Max Activating Token Index: 596

Text #16

Max Range: 1.4441. Min Range: -1.4441

Max Act: 1.1817. Min Act: -0.0001

Data Index: 1406423 (Python Code)

Max Activating Token Index: 425

Text #17

Max Range: 1.4441. Min Range: -1.4441

Max Act: 1.1181. Min Act: -0.0001

Data Index: 1367441 (Python Code)

Max Activating Token Index: 352

Text #18

Max Range: 1.4441. Min Range: -1.4441

Max Act: 1.1811. Min Act: -0.0001

Data Index: 1386299 (Python Code)

Max Activating Token Index: 32

Text #19

Max Range: 1.4441. Min Range: -1.4441

Max Act: 1.1384. Min Act: -0.0001

Data Index: 1400543 (Python Code)

Max Activating Token Index: 182