Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1875 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.0369. Min Range: -1.0369

Max Act: 1.0369. Min Act: -0.0001

Data Index: 1541321 (Python Code)

Max Activating Token Index: 189

Text #1

Max Range: 1.0369. Min Range: -1.0369

Max Act: 0.9433. Min Act: -0.0001

Data Index: 1380814 (Python Code)

Max Activating Token Index: 69

Text #2

Max Range: 1.0369. Min Range: -1.0369

Max Act: 0.9217. Min Act: -0.0001

Data Index: 1618064 (Python Code)

Max Activating Token Index: 401

Text #3

Max Range: 1.0369. Min Range: -1.0369

Max Act: 0.8123. Min Act: -0.0001

Data Index: 1458940 (Python Code)

Max Activating Token Index: 836

Text #4

Max Range: 1.0369. Min Range: -1.0369

Max Act: 0.7585. Min Act: -0.0001

Data Index: 1410178 (Python Code)

Max Activating Token Index: 718

Text #5

Max Range: 1.0369. Min Range: -1.0369

Max Act: 0.7802. Min Act: -0.0001

Data Index: 1362540 (Python Code)

Max Activating Token Index: 865

Text #6

Max Range: 1.0369. Min Range: -1.0369

Max Act: 0.7093. Min Act: -0.0001

Data Index: 1505292 (Python Code)

Max Activating Token Index: 928

Text #7

Max Range: 1.0369. Min Range: -1.0369

Max Act: 0.7362. Min Act: -0.0001

Data Index: 1480947 (Python Code)

Max Activating Token Index: 70

Text #8

Max Range: 1.0369. Min Range: -1.0369

Max Act: 0.7353. Min Act: -0.0001

Data Index: 1540561 (Python Code)

Max Activating Token Index: 81

Text #9

Max Range: 1.0369. Min Range: -1.0369

Max Act: 0.7524. Min Act: -0.0001

Data Index: 1462885 (Python Code)

Max Activating Token Index: 975

Text #10

Max Range: 1.0369. Min Range: -1.0369

Max Act: 0.7014. Min Act: -0.0001

Data Index: 1400814 (Python Code)

Max Activating Token Index: 1001

Text #11

Max Range: 1.0369. Min Range: -1.0369

Max Act: 0.7059. Min Act: -0.0001

Data Index: 1459263 (Python Code)

Max Activating Token Index: 1007

Text #12

Max Range: 1.0369. Min Range: -1.0369

Max Act: 0.7167. Min Act: -0.0001

Data Index: 1650906 (Python Code)

Max Activating Token Index: 960

Text #13

Max Range: 1.0369. Min Range: -1.0369

Max Act: 0.7078. Min Act: -0.0001

Data Index: 1501264 (Python Code)

Max Activating Token Index: 32

Text #14

Max Range: 1.0369. Min Range: -1.0369

Max Act: 0.7030. Min Act: -0.0001

Data Index: 1623696 (Python Code)

Max Activating Token Index: 1020

Text #15

Max Range: 1.0369. Min Range: -1.0369

Max Act: 0.6673. Min Act: -0.0001

Data Index: 1525520 (Python Code)

Max Activating Token Index: 20

Text #16

Max Range: 1.0369. Min Range: -1.0369

Max Act: 0.6644. Min Act: -0.0001

Data Index: 1590144 (Python Code)

Max Activating Token Index: 538

Text #17

Max Range: 1.0369. Min Range: -1.0369

Max Act: 0.6508. Min Act: -0.0001

Data Index: 1441487 (Python Code)

Max Activating Token Index: 671

Text #18

Max Range: 1.0369. Min Range: -1.0369

Max Act: 0.6640. Min Act: -0.0001

Data Index: 1576556 (Python Code)

Max Activating Token Index: 57

Text #19

Max Range: 1.0369. Min Range: -1.0369

Max Act: 0.7598. Min Act: -0.0001

Data Index: 1485245 (Python Code)

Max Activating Token Index: 396