Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 126 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.6650. Min Range: -3.6650

Max Act: 3.6337. Min Act: -0.1700

Data Index: 1647115 (Python Code)

Max Activating Token Index: 97

Text #1

Max Range: 3.6650. Min Range: -3.6650

Max Act: 3.6650. Min Act: -0.1700

Data Index: 1565917 (Python Code)

Max Activating Token Index: 92

Text #2

Max Range: 3.6650. Min Range: -3.6650

Max Act: 3.6650. Min Act: -0.1700

Data Index: 1398383 (Python Code)

Max Activating Token Index: 93

Text #3

Max Range: 3.6650. Min Range: -3.6650

Max Act: 3.6337. Min Act: -0.1700

Data Index: 1392617 (Python Code)

Max Activating Token Index: 87

Text #4

Max Range: 3.6650. Min Range: -3.6650

Max Act: 3.6337. Min Act: -0.1700

Data Index: 1388866 (Python Code)

Max Activating Token Index: 94

Text #5

Max Range: 3.6650. Min Range: -3.6650

Max Act: 3.5710. Min Act: -0.1700

Data Index: 1497525 (Python Code)

Max Activating Token Index: 202

Text #6

Max Range: 3.6650. Min Range: -3.6650

Max Act: 3.6024. Min Act: -0.1700

Data Index: 1618968 (Python Code)

Max Activating Token Index: 89

Text #7

Max Range: 3.6650. Min Range: -3.6650

Max Act: 3.5710. Min Act: -0.1700

Data Index: 1508935 (Python Code)

Max Activating Token Index: 69

Text #8

Max Range: 3.6650. Min Range: -3.6650

Max Act: 3.6024. Min Act: -0.1700

Data Index: 1501556 (Python Code)

Max Activating Token Index: 113

Text #9

Max Range: 3.6650. Min Range: -3.6650

Max Act: 3.5710. Min Act: -0.1700

Data Index: 1472872 (Python Code)

Max Activating Token Index: 356

Text #10

Max Range: 3.6650. Min Range: -3.6650

Max Act: 3.6024. Min Act: -0.1700

Data Index: 1383519 (Python Code)

Max Activating Token Index: 64

Text #11

Max Range: 3.6650. Min Range: -3.6650

Max Act: 3.6024. Min Act: -0.1700

Data Index: 1553943 (Python Code)

Max Activating Token Index: 471

Text #12

Max Range: 3.6650. Min Range: -3.6650

Max Act: 3.6337. Min Act: -0.1700

Data Index: 1421761 (Python Code)

Max Activating Token Index: 100

Text #13

Max Range: 3.6650. Min Range: -3.6650

Max Act: 3.6337. Min Act: -0.1700

Data Index: 1403377 (Python Code)

Max Activating Token Index: 697

Text #14

Max Range: 3.6650. Min Range: -3.6650

Max Act: 3.5710. Min Act: -0.1700

Data Index: 1533994 (Python Code)

Max Activating Token Index: 69

Text #15

Max Range: 3.6650. Min Range: -3.6650

Max Act: 3.6337. Min Act: -0.1700

Data Index: 1532412 (Python Code)

Max Activating Token Index: 100

Text #16

Max Range: 3.6650. Min Range: -3.6650

Max Act: 3.6024. Min Act: -0.1700

Data Index: 804768 (C4 (Web Text))

Max Activating Token Index: 493

Text #17

Max Range: 3.6650. Min Range: -3.6650

Max Act: 3.5397. Min Act: -0.1700

Data Index: 1531946 (Python Code)

Max Activating Token Index: 162

Text #18

Max Range: 3.6650. Min Range: -3.6650

Max Act: 3.5397. Min Act: -0.1700

Data Index: 1508394 (Python Code)

Max Activating Token Index: 394

Text #19

Max Range: 3.6650. Min Range: -3.6650

Max Act: 3.5710. Min Act: -0.1700

Data Index: 1528202 (Python Code)

Max Activating Token Index: 66