Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1920 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.0934. Min Range: -3.0934

Max Act: 3.0934. Min Act: -0.1700

Data Index: 1103051 (C4 (Web Text))

Max Activating Token Index: 25

Text #1

Max Range: 3.0934. Min Range: -3.0934

Max Act: 2.9195. Min Act: -0.1700

Data Index: 622579 (C4 (Web Text))

Max Activating Token Index: 361

Text #2

Max Range: 3.0934. Min Range: -3.0934

Max Act: 2.8719. Min Act: -0.1700

Data Index: 866524 (C4 (Web Text))

Max Activating Token Index: 383

Text #3

Max Range: 3.0934. Min Range: -3.0934

Max Act: 2.8083. Min Act: -0.1700

Data Index: 280225 (C4 (Web Text))

Max Activating Token Index: 276

Text #4

Max Range: 3.0934. Min Range: -3.0934

Max Act: 2.6325. Min Act: -0.1700

Data Index: 727084 (C4 (Web Text))

Max Activating Token Index: 3

Text #5

Max Range: 3.0934. Min Range: -3.0934

Max Act: 2.5842. Min Act: -0.1700

Data Index: 1572029 (Python Code)

Max Activating Token Index: 60

Text #6

Max Range: 3.0934. Min Range: -3.0934

Max Act: 2.5842. Min Act: -0.1700

Data Index: 1524786 (Python Code)

Max Activating Token Index: 39

Text #7

Max Range: 3.0934. Min Range: -3.0934

Max Act: 2.5842. Min Act: -0.1700

Data Index: 1590514 (Python Code)

Max Activating Token Index: 89

Text #8

Max Range: 3.0934. Min Range: -3.0934

Max Act: 2.5842. Min Act: -0.1700

Data Index: 1529754 (Python Code)

Max Activating Token Index: 71

Text #9

Max Range: 3.0934. Min Range: -3.0934

Max Act: 2.5681. Min Act: -0.1700

Data Index: 250059 (C4 (Web Text))

Max Activating Token Index: 8

Text #10

Max Range: 3.0934. Min Range: -3.0934

Max Act: 2.5681. Min Act: -0.1700

Data Index: 1608015 (Python Code)

Max Activating Token Index: 57

Text #11

Max Range: 3.0934. Min Range: -3.0934

Max Act: 2.5520. Min Act: -0.1700

Data Index: 1610221 (Python Code)

Max Activating Token Index: 34

Text #12

Max Range: 3.0934. Min Range: -3.0934

Max Act: 2.5520. Min Act: -0.1700

Data Index: 1599663 (Python Code)

Max Activating Token Index: 760

Text #13

Max Range: 3.0934. Min Range: -3.0934

Max Act: 2.5681. Min Act: -0.1700

Data Index: 1447578 (Python Code)

Max Activating Token Index: 80

Text #14

Max Range: 3.0934. Min Range: -3.0934

Max Act: 2.5681. Min Act: -0.1700

Data Index: 1542654 (Python Code)

Max Activating Token Index: 34

Text #15

Max Range: 3.0934. Min Range: -3.0934

Max Act: 2.5520. Min Act: -0.1700

Data Index: 1404662 (Python Code)

Max Activating Token Index: 53

Text #16

Max Range: 3.0934. Min Range: -3.0934

Max Act: 2.5520. Min Act: -0.1700

Data Index: 1519847 (Python Code)

Max Activating Token Index: 67

Text #17

Max Range: 3.0934. Min Range: -3.0934

Max Act: 2.5520. Min Act: -0.1700

Data Index: 97536 (C4 (Web Text))

Max Activating Token Index: 2

Text #18

Max Range: 3.0934. Min Range: -3.0934

Max Act: 2.5520. Min Act: -0.1700

Data Index: 1432456 (Python Code)

Max Activating Token Index: 25

Text #19

Max Range: 3.0934. Min Range: -3.0934

Max Act: 2.5358. Min Act: -0.1700

Data Index: 1361439 (Python Code)

Max Activating Token Index: 19