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

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

Neuron 1082 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0801. Min Range: -3.0801

Max Act: 3.0801. Min Act: -0.1700

Data Index: 1471140 (Python Code)

Max Activating Token Index: 5

Text #1

Max Range: 3.0801. Min Range: -3.0801

Max Act: 3.0643. Min Act: -0.1700

Data Index: 1639224 (Python Code)

Max Activating Token Index: 7

Text #2

Max Range: 3.0801. Min Range: -3.0801

Max Act: 3.0327. Min Act: -0.1700

Data Index: 1635697 (Python Code)

Max Activating Token Index: 6

Text #3

Max Range: 3.0801. Min Range: -3.0801

Max Act: 3.0169. Min Act: -0.1700

Data Index: 1639317 (Python Code)

Max Activating Token Index: 6

Text #4

Max Range: 3.0801. Min Range: -3.0801

Max Act: 3.0011. Min Act: -0.1700

Data Index: 85992 (C4 (Web Text))

Max Activating Token Index: 34

Text #5

Max Range: 3.0801. Min Range: -3.0801

Max Act: 3.0011. Min Act: -0.1700

Data Index: 1565794 (Python Code)

Max Activating Token Index: 874

Text #6

Max Range: 3.0801. Min Range: -3.0801

Max Act: 2.9853. Min Act: -0.1700

Data Index: 1552081 (Python Code)

Max Activating Token Index: 7

Text #7

Max Range: 3.0801. Min Range: -3.0801

Max Act: 2.9853. Min Act: -0.1700

Data Index: 1613537 (Python Code)

Max Activating Token Index: 7

Text #8

Max Range: 3.0801. Min Range: -3.0801

Max Act: 2.9853. Min Act: -0.1700

Data Index: 1500941 (Python Code)

Max Activating Token Index: 12

Text #9

Max Range: 3.0801. Min Range: -3.0801

Max Act: 3.0011. Min Act: -0.1700

Data Index: 1341033 (C4 (Web Text))

Max Activating Token Index: 7

Text #10

Max Range: 3.0801. Min Range: -3.0801

Max Act: 2.9695. Min Act: -0.1700

Data Index: 1537220 (Python Code)

Max Activating Token Index: 3

Text #11

Max Range: 3.0801. Min Range: -3.0801

Max Act: 2.9695. Min Act: -0.1700

Data Index: 1467225 (Python Code)

Max Activating Token Index: 2

Text #12

Max Range: 3.0801. Min Range: -3.0801

Max Act: 2.9695. Min Act: -0.1700

Data Index: 1590822 (Python Code)

Max Activating Token Index: 2

Text #13

Max Range: 3.0801. Min Range: -3.0801

Max Act: 2.9537. Min Act: -0.1700

Data Index: 1516469 (Python Code)

Max Activating Token Index: 9

Text #14

Max Range: 3.0801. Min Range: -3.0801

Max Act: 2.9537. Min Act: -0.1700

Data Index: 1452449 (Python Code)

Max Activating Token Index: 26

Text #15

Max Range: 3.0801. Min Range: -3.0801

Max Act: 2.9378. Min Act: -0.1700

Data Index: 1407598 (Python Code)

Max Activating Token Index: 12

Text #16

Max Range: 3.0801. Min Range: -3.0801

Max Act: 2.9220. Min Act: -0.1700

Data Index: 1380082 (Python Code)

Max Activating Token Index: 9

Text #17

Max Range: 3.0801. Min Range: -3.0801

Max Act: 2.9220. Min Act: -0.1700

Data Index: 1475957 (Python Code)

Max Activating Token Index: 4

Text #18

Max Range: 3.0801. Min Range: -3.0801

Max Act: 2.9220. Min Act: -0.1700

Data Index: 1374987 (Python Code)

Max Activating Token Index: 6

Text #19

Max Range: 3.0801. Min Range: -3.0801

Max Act: 2.9061. Min Act: -0.1700

Data Index: 1531653 (Python Code)

Max Activating Token Index: 38