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

Dataset: Open Web Text

Neuron 2833 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: 1.3748. Min Range: -1.3748

Max Act: 1.3748. Min Act: -0.1700

Data Index: 42921 (Open Web Text)

Max Activating Token Index: 625

Text #1

Max Range: 1.3748. Min Range: -1.3748

Max Act: 1.3576. Min Act: -0.1700

Data Index: 42922 (Open Web Text)

Max Activating Token Index: 618

Text #2

Max Range: 1.3748. Min Range: -1.3748

Max Act: 1.2042. Min Act: -0.1700

Data Index: 6054347 (Open Web Text)

Max Activating Token Index: 638

Text #3

Max Range: 1.3748. Min Range: -1.3748

Max Act: 1.2021. Min Act: -0.1700

Data Index: 6054348 (Open Web Text)

Max Activating Token Index: 616

Text #4

Max Range: 1.3748. Min Range: -1.3748

Max Act: 1.1979. Min Act: -0.1700

Data Index: 5673721 (Open Web Text)

Max Activating Token Index: 618

Text #5

Max Range: 1.3748. Min Range: -1.3748

Max Act: 1.1950. Min Act: -0.1700

Data Index: 5838085 (Open Web Text)

Max Activating Token Index: 624

Text #6

Max Range: 1.3748. Min Range: -1.3748

Max Act: 1.1913. Min Act: -0.1700

Data Index: 5679730 (Open Web Text)

Max Activating Token Index: 618

Text #7

Max Range: 1.3748. Min Range: -1.3748

Max Act: 1.1810. Min Act: -0.1700

Data Index: 4229998 (Open Web Text)

Max Activating Token Index: 640

Text #8

Max Range: 1.3748. Min Range: -1.3748

Max Act: 1.1619. Min Act: -0.1700

Data Index: 5673722 (Open Web Text)

Max Activating Token Index: 604

Text #9

Max Range: 1.3748. Min Range: -1.3748

Max Act: 1.1768. Min Act: -0.1700

Data Index: 8686167 (Open Web Text)

Max Activating Token Index: 609

Text #10

Max Range: 1.3748. Min Range: -1.3748

Max Act: 1.1593. Min Act: -0.1700

Data Index: 2223552 (Open Web Text)

Max Activating Token Index: 627

Text #11

Max Range: 1.3748. Min Range: -1.3748

Max Act: 1.1641. Min Act: -0.1700

Data Index: 3756934 (Open Web Text)

Max Activating Token Index: 577

Text #12

Max Range: 1.3748. Min Range: -1.3748

Max Act: 1.1275. Min Act: -0.1700

Data Index: 5934388 (Open Web Text)

Max Activating Token Index: 646

Text #13

Max Range: 1.3748. Min Range: -1.3748

Max Act: 1.1388. Min Act: -0.1700

Data Index: 2079165 (Open Web Text)

Max Activating Token Index: 619

Text #14

Max Range: 1.3748. Min Range: -1.3748

Max Act: 1.1401. Min Act: -0.1700

Data Index: 4230001 (Open Web Text)

Max Activating Token Index: 625

Text #15

Max Range: 1.3748. Min Range: -1.3748

Max Act: 1.1329. Min Act: -0.1700

Data Index: 8781142 (Open Web Text)

Max Activating Token Index: 629

Text #16

Max Range: 1.3748. Min Range: -1.3748

Max Act: 1.1408. Min Act: -0.1700

Data Index: 4230004 (Open Web Text)

Max Activating Token Index: 607

Text #17

Max Range: 1.3748. Min Range: -1.3748

Max Act: 1.1420. Min Act: -0.1700

Data Index: 1180567 (Open Web Text)

Max Activating Token Index: 611

Text #18

Max Range: 1.3748. Min Range: -1.3748

Max Act: 1.1299. Min Act: -0.1700

Data Index: 5906857 (Open Web Text)

Max Activating Token Index: 634

Text #19

Max Range: 1.3748. Min Range: -1.3748

Max Act: 1.1161. Min Act: -0.1700

Data Index: 5056209 (Open Web Text)

Max Activating Token Index: 627