Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 2672 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 3.2052. Min Range: -3.2052

Max Act: 3.2052. Min Act: -0.1700

Data Index: 4453177 (Open Web Text)

Max Activating Token Index: 2

Text #1

Max Range: 3.2052. Min Range: -3.2052

Max Act: 3.1794. Min Act: -0.1700

Data Index: 8624579 (Open Web Text)

Max Activating Token Index: 2

Text #2

Max Range: 3.2052. Min Range: -3.2052

Max Act: 3.1343. Min Act: -0.1700

Data Index: 4892303 (Open Web Text)

Max Activating Token Index: 2

Text #3

Max Range: 3.2052. Min Range: -3.2052

Max Act: 3.1378. Min Act: -0.1700

Data Index: 7758864 (Open Web Text)

Max Activating Token Index: 11

Text #4

Max Range: 3.2052. Min Range: -3.2052

Max Act: 3.1148. Min Act: -0.1700

Data Index: 4196078 (Open Web Text)

Max Activating Token Index: 3

Text #5

Max Range: 3.2052. Min Range: -3.2052

Max Act: 3.1026. Min Act: -0.1700

Data Index: 8127407 (Open Web Text)

Max Activating Token Index: 2

Text #6

Max Range: 3.2052. Min Range: -3.2052

Max Act: 3.1041. Min Act: -0.1700

Data Index: 2905769 (Open Web Text)

Max Activating Token Index: 2

Text #7

Max Range: 3.2052. Min Range: -3.2052

Max Act: 3.0855. Min Act: -0.1700

Data Index: 3584899 (Open Web Text)

Max Activating Token Index: 2

Text #8

Max Range: 3.2052. Min Range: -3.2052

Max Act: 3.0833. Min Act: -0.1700

Data Index: 4792358 (Open Web Text)

Max Activating Token Index: 3

Text #9

Max Range: 3.2052. Min Range: -3.2052

Max Act: 3.0855. Min Act: -0.1700

Data Index: 8290743 (Open Web Text)

Max Activating Token Index: 2

Text #10

Max Range: 3.2052. Min Range: -3.2052

Max Act: 3.0920. Min Act: -0.1700

Data Index: 911764 (Open Web Text)

Max Activating Token Index: 4

Text #11

Max Range: 3.2052. Min Range: -3.2052

Max Act: 3.0762. Min Act: -0.1700

Data Index: 7493273 (Open Web Text)

Max Activating Token Index: 3

Text #12

Max Range: 3.2052. Min Range: -3.2052

Max Act: 3.0641. Min Act: -0.1700

Data Index: 3171128 (Open Web Text)

Max Activating Token Index: 57

Text #13

Max Range: 3.2052. Min Range: -3.2052

Max Act: 3.0738. Min Act: -0.1700

Data Index: 7448992 (Open Web Text)

Max Activating Token Index: 3

Text #14

Max Range: 3.2052. Min Range: -3.2052

Max Act: 3.0795. Min Act: -0.1700

Data Index: 3281427 (Open Web Text)

Max Activating Token Index: 3

Text #15

Max Range: 3.2052. Min Range: -3.2052

Max Act: 3.0723. Min Act: -0.1700

Data Index: 376337 (Open Web Text)

Max Activating Token Index: 42

Text #16

Max Range: 3.2052. Min Range: -3.2052

Max Act: 3.0761. Min Act: -0.1700

Data Index: 7295447 (Open Web Text)

Max Activating Token Index: 25

Text #17

Max Range: 3.2052. Min Range: -3.2052

Max Act: 3.0687. Min Act: -0.1700

Data Index: 5337227 (Open Web Text)

Max Activating Token Index: 60

Text #18

Max Range: 3.2052. Min Range: -3.2052

Max Act: 3.0648. Min Act: -0.1700

Data Index: 5966699 (Open Web Text)

Max Activating Token Index: 2

Text #19

Max Range: 3.2052. Min Range: -3.2052

Max Act: 3.0736. Min Act: -0.1700

Data Index: 1708422 (Open Web Text)

Max Activating Token Index: 14