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

Dataset: Open Web Text

Neuron 866 in Layer 3

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: 4.2600. Min Range: -4.2600

Max Act: 4.2600. Min Act: -0.1700

Data Index: 4312911 (Open Web Text)

Max Activating Token Index: 364

Text #1

Max Range: 4.2600. Min Range: -4.2600

Max Act: 4.2572. Min Act: -0.1700

Data Index: 296921 (Open Web Text)

Max Activating Token Index: 675

Text #2

Max Range: 4.2600. Min Range: -4.2600

Max Act: 4.2191. Min Act: -0.1700

Data Index: 3221802 (Open Web Text)

Max Activating Token Index: 2

Text #3

Max Range: 4.2600. Min Range: -4.2600

Max Act: 4.1870. Min Act: -0.1700

Data Index: 8784913 (Open Web Text)

Max Activating Token Index: 358

Text #4

Max Range: 4.2600. Min Range: -4.2600

Max Act: 4.1650. Min Act: -0.1700

Data Index: 1765425 (Open Web Text)

Max Activating Token Index: 356

Text #5

Max Range: 4.2600. Min Range: -4.2600

Max Act: 4.1732. Min Act: -0.1700

Data Index: 3219922 (Open Web Text)

Max Activating Token Index: 23

Text #6

Max Range: 4.2600. Min Range: -4.2600

Max Act: 4.1401. Min Act: -0.1700

Data Index: 1666576 (Open Web Text)

Max Activating Token Index: 100

Text #7

Max Range: 4.2600. Min Range: -4.2600

Max Act: 4.1371. Min Act: -0.1700

Data Index: 2584212 (Open Web Text)

Max Activating Token Index: 2

Text #8

Max Range: 4.2600. Min Range: -4.2600

Max Act: 4.1277. Min Act: -0.1700

Data Index: 7943213 (Open Web Text)

Max Activating Token Index: 992

Text #9

Max Range: 4.2600. Min Range: -4.2600

Max Act: 4.1482. Min Act: -0.1700

Data Index: 6960109 (Open Web Text)

Max Activating Token Index: 692

Text #10

Max Range: 4.2600. Min Range: -4.2600

Max Act: 4.1404. Min Act: -0.1700

Data Index: 1809907 (Open Web Text)

Max Activating Token Index: 446

Text #11

Max Range: 4.2600. Min Range: -4.2600

Max Act: 4.1447. Min Act: -0.1700

Data Index: 6251008 (Open Web Text)

Max Activating Token Index: 417

Text #12

Max Range: 4.2600. Min Range: -4.2600

Max Act: 4.1185. Min Act: -0.1700

Data Index: 8404648 (Open Web Text)

Max Activating Token Index: 418

Text #13

Max Range: 4.2600. Min Range: -4.2600

Max Act: 4.0769. Min Act: -0.1700

Data Index: 1407449 (Open Web Text)

Max Activating Token Index: 999

Text #14

Max Range: 4.2600. Min Range: -4.2600

Max Act: 4.1296. Min Act: -0.1700

Data Index: 2233361 (Open Web Text)

Max Activating Token Index: 729

Text #15

Max Range: 4.2600. Min Range: -4.2600

Max Act: 4.1297. Min Act: -0.1700

Data Index: 1879845 (Open Web Text)

Max Activating Token Index: 775

Text #16

Max Range: 4.2600. Min Range: -4.2600

Max Act: 4.0988. Min Act: -0.1700

Data Index: 6192141 (Open Web Text)

Max Activating Token Index: 618

Text #17

Max Range: 4.2600. Min Range: -4.2600

Max Act: 4.0960. Min Act: -0.1700

Data Index: 3259885 (Open Web Text)

Max Activating Token Index: 101

Text #18

Max Range: 4.2600. Min Range: -4.2600

Max Act: 4.0615. Min Act: -0.1700

Data Index: 5631984 (Open Web Text)

Max Activating Token Index: 379

Text #19

Max Range: 4.2600. Min Range: -4.2600

Max Act: 4.0634. Min Act: -0.1700

Data Index: 6741393 (Open Web Text)

Max Activating Token Index: 783