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

Dataset: Open Web Text

Neuron 2732 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: 4.9007. Min Range: -4.9007

Max Act: 4.9007. Min Act: -0.1700

Data Index: 4041828 (Open Web Text)

Max Activating Token Index: 5

Text #1

Max Range: 4.9007. Min Range: -4.9007

Max Act: 4.8767. Min Act: -0.1699

Data Index: 6010319 (Open Web Text)

Max Activating Token Index: 20

Text #2

Max Range: 4.9007. Min Range: -4.9007

Max Act: 4.8765. Min Act: -0.1700

Data Index: 7032631 (Open Web Text)

Max Activating Token Index: 843

Text #3

Max Range: 4.9007. Min Range: -4.9007

Max Act: 4.8921. Min Act: -0.1700

Data Index: 7125813 (Open Web Text)

Max Activating Token Index: 9

Text #4

Max Range: 4.9007. Min Range: -4.9007

Max Act: 4.8862. Min Act: -0.1700

Data Index: 2677399 (Open Web Text)

Max Activating Token Index: 4

Text #5

Max Range: 4.9007. Min Range: -4.9007

Max Act: 4.8564. Min Act: -0.1700

Data Index: 7655400 (Open Web Text)

Max Activating Token Index: 812

Text #6

Max Range: 4.9007. Min Range: -4.9007

Max Act: 4.8527. Min Act: -0.1700

Data Index: 5936049 (Open Web Text)

Max Activating Token Index: 15

Text #7

Max Range: 4.9007. Min Range: -4.9007

Max Act: 4.8428. Min Act: -0.1700

Data Index: 5529605 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 4.9007. Min Range: -4.9007

Max Act: 4.8450. Min Act: -0.1700

Data Index: 2519883 (Open Web Text)

Max Activating Token Index: 7

Text #9

Max Range: 4.9007. Min Range: -4.9007

Max Act: 4.8602. Min Act: -0.1700

Data Index: 1577833 (Open Web Text)

Max Activating Token Index: 5

Text #10

Max Range: 4.9007. Min Range: -4.9007

Max Act: 4.8389. Min Act: -0.1700

Data Index: 3076299 (Open Web Text)

Max Activating Token Index: 17

Text #11

Max Range: 4.9007. Min Range: -4.9007

Max Act: 4.8277. Min Act: -0.1700

Data Index: 1705340 (Open Web Text)

Max Activating Token Index: 5

Text #12

Max Range: 4.9007. Min Range: -4.9007

Max Act: 4.8131. Min Act: -0.1700

Data Index: 3264103 (Open Web Text)

Max Activating Token Index: 922

Text #13

Max Range: 4.9007. Min Range: -4.9007

Max Act: 4.8063. Min Act: -0.1700

Data Index: 2948633 (Open Web Text)

Max Activating Token Index: 6

Text #14

Max Range: 4.9007. Min Range: -4.9007

Max Act: 4.8116. Min Act: -0.1700

Data Index: 380700 (Open Web Text)

Max Activating Token Index: 15

Text #15

Max Range: 4.9007. Min Range: -4.9007

Max Act: 4.8053. Min Act: -0.1700

Data Index: 2936711 (Open Web Text)

Max Activating Token Index: 6

Text #16

Max Range: 4.9007. Min Range: -4.9007

Max Act: 4.8266. Min Act: -0.1700

Data Index: 5740950 (Open Web Text)

Max Activating Token Index: 6

Text #17

Max Range: 4.9007. Min Range: -4.9007

Max Act: 4.8195. Min Act: -0.1700

Data Index: 5698566 (Open Web Text)

Max Activating Token Index: 6

Text #18

Max Range: 4.9007. Min Range: -4.9007

Max Act: 4.8262. Min Act: -0.1700

Data Index: 2528637 (Open Web Text)

Max Activating Token Index: 9

Text #19

Max Range: 4.9007. Min Range: -4.9007

Max Act: 4.8131. Min Act: -0.1700

Data Index: 2450630 (Open Web Text)

Max Activating Token Index: 13