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

Dataset: Open Web Text

Neuron 1721 in Layer 2

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: 4.1928. Min Range: -4.1928

Max Act: 4.1928. Min Act: -0.1700

Data Index: 5297629 (Open Web Text)

Max Activating Token Index: 375

Text #1

Max Range: 4.1928. Min Range: -4.1928

Max Act: 4.1572. Min Act: -0.1700

Data Index: 5788680 (Open Web Text)

Max Activating Token Index: 868

Text #2

Max Range: 4.1928. Min Range: -4.1928

Max Act: 4.1406. Min Act: -0.1700

Data Index: 888215 (Open Web Text)

Max Activating Token Index: 24

Text #3

Max Range: 4.1928. Min Range: -4.1928

Max Act: 4.0960. Min Act: -0.1700

Data Index: 7708618 (Open Web Text)

Max Activating Token Index: 53

Text #4

Max Range: 4.1928. Min Range: -4.1928

Max Act: 4.0690. Min Act: -0.1700

Data Index: 1226093 (Open Web Text)

Max Activating Token Index: 8

Text #5

Max Range: 4.1928. Min Range: -4.1928

Max Act: 4.0886. Min Act: -0.1700

Data Index: 3693560 (Open Web Text)

Max Activating Token Index: 139

Text #6

Max Range: 4.1928. Min Range: -4.1928

Max Act: 4.0713. Min Act: -0.1700

Data Index: 3303047 (Open Web Text)

Max Activating Token Index: 202

Text #7

Max Range: 4.1928. Min Range: -4.1928

Max Act: 4.0440. Min Act: -0.1700

Data Index: 2369820 (Open Web Text)

Max Activating Token Index: 368

Text #8

Max Range: 4.1928. Min Range: -4.1928

Max Act: 4.0459. Min Act: -0.1700

Data Index: 5089964 (Open Web Text)

Max Activating Token Index: 95

Text #9

Max Range: 4.1928. Min Range: -4.1928

Max Act: 4.0723. Min Act: -0.1700

Data Index: 8272122 (Open Web Text)

Max Activating Token Index: 54

Text #10

Max Range: 4.1928. Min Range: -4.1928

Max Act: 3.9848. Min Act: -0.1700

Data Index: 4383981 (Open Web Text)

Max Activating Token Index: 21

Text #11

Max Range: 4.1928. Min Range: -4.1928

Max Act: 4.0205. Min Act: -0.1700

Data Index: 5257772 (Open Web Text)

Max Activating Token Index: 925

Text #12

Max Range: 4.1928. Min Range: -4.1928

Max Act: 3.9985. Min Act: -0.1700

Data Index: 3579598 (Open Web Text)

Max Activating Token Index: 24

Text #13

Max Range: 4.1928. Min Range: -4.1928

Max Act: 3.9975. Min Act: -0.1700

Data Index: 1473091 (Open Web Text)

Max Activating Token Index: 64

Text #14

Max Range: 4.1928. Min Range: -4.1928

Max Act: 4.0219. Min Act: -0.1700

Data Index: 4610936 (Open Web Text)

Max Activating Token Index: 466

Text #15

Max Range: 4.1928. Min Range: -4.1928

Max Act: 3.9980. Min Act: -0.1700

Data Index: 3085952 (Open Web Text)

Max Activating Token Index: 730

Text #16

Max Range: 4.1928. Min Range: -4.1928

Max Act: 4.0125. Min Act: -0.1700

Data Index: 1877135 (Open Web Text)

Max Activating Token Index: 433

Text #17

Max Range: 4.1928. Min Range: -4.1928

Max Act: 3.9782. Min Act: -0.1700

Data Index: 5438182 (Open Web Text)

Max Activating Token Index: 30

Text #18

Max Range: 4.1928. Min Range: -4.1928

Max Act: 3.9782. Min Act: -0.1700

Data Index: 5598612 (Open Web Text)

Max Activating Token Index: 15

Text #19

Max Range: 4.1928. Min Range: -4.1928

Max Act: 3.9915. Min Act: -0.1700

Data Index: 7145321 (Open Web Text)

Max Activating Token Index: 65