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

Dataset: Open Web Text

Neuron 911 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: 4.1300. Min Range: -4.1300

Max Act: 4.1300. Min Act: -0.1700

Data Index: 7720728 (Open Web Text)

Max Activating Token Index: 2

Text #1

Max Range: 4.1300. Min Range: -4.1300

Max Act: 4.0835. Min Act: -0.1700

Data Index: 622808 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 4.1300. Min Range: -4.1300

Max Act: 4.0292. Min Act: -0.1700

Data Index: 950795 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 4.1300. Min Range: -4.1300

Max Act: 4.0284. Min Act: -0.1700

Data Index: 5431212 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 4.1300. Min Range: -4.1300

Max Act: 4.0001. Min Act: -0.1700

Data Index: 6829653 (Open Web Text)

Max Activating Token Index: 2

Text #5

Max Range: 4.1300. Min Range: -4.1300

Max Act: 4.0157. Min Act: -0.1700

Data Index: 6987998 (Open Web Text)

Max Activating Token Index: 3

Text #6

Max Range: 4.1300. Min Range: -4.1300

Max Act: 4.0001. Min Act: -0.1700

Data Index: 7240186 (Open Web Text)

Max Activating Token Index: 2

Text #7

Max Range: 4.1300. Min Range: -4.1300

Max Act: 3.9873. Min Act: -0.1700

Data Index: 4180651 (Open Web Text)

Max Activating Token Index: 2

Text #8

Max Range: 4.1300. Min Range: -4.1300

Max Act: 4.0001. Min Act: -0.1700

Data Index: 7136571 (Open Web Text)

Max Activating Token Index: 2

Text #9

Max Range: 4.1300. Min Range: -4.1300

Max Act: 4.0001. Min Act: -0.1700

Data Index: 5692551 (Open Web Text)

Max Activating Token Index: 2

Text #10

Max Range: 4.1300. Min Range: -4.1300

Max Act: 4.0001. Min Act: -0.1700

Data Index: 5569967 (Open Web Text)

Max Activating Token Index: 2

Text #11

Max Range: 4.1300. Min Range: -4.1300

Max Act: 3.9947. Min Act: -0.1700

Data Index: 2395218 (Open Web Text)

Max Activating Token Index: 2

Text #12

Max Range: 4.1300. Min Range: -4.1300

Max Act: 4.0001. Min Act: -0.1700

Data Index: 3577932 (Open Web Text)

Max Activating Token Index: 2

Text #13

Max Range: 4.1300. Min Range: -4.1300

Max Act: 4.0001. Min Act: -0.1700

Data Index: 2089623 (Open Web Text)

Max Activating Token Index: 2

Text #14

Max Range: 4.1300. Min Range: -4.1300

Max Act: 4.0001. Min Act: -0.1700

Data Index: 1792566 (Open Web Text)

Max Activating Token Index: 2

Text #15

Max Range: 4.1300. Min Range: -4.1300

Max Act: 4.0001. Min Act: -0.1700

Data Index: 4887553 (Open Web Text)

Max Activating Token Index: 2

Text #16

Max Range: 4.1300. Min Range: -4.1300

Max Act: 4.0001. Min Act: -0.1700

Data Index: 7731138 (Open Web Text)

Max Activating Token Index: 2

Text #17

Max Range: 4.1300. Min Range: -4.1300

Max Act: 4.0001. Min Act: -0.1700

Data Index: 3168654 (Open Web Text)

Max Activating Token Index: 2

Text #18

Max Range: 4.1300. Min Range: -4.1300

Max Act: 3.9559. Min Act: -0.1700

Data Index: 3679891 (Open Web Text)

Max Activating Token Index: 5

Text #19

Max Range: 4.1300. Min Range: -4.1300

Max Act: 3.9709. Min Act: -0.1700

Data Index: 3933411 (Open Web Text)

Max Activating Token Index: 5