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

Dataset: Open Web Text

Neuron 898 in Layer 6

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: 5.2570. Min Range: -5.2570

Max Act: 5.2570. Min Act: -0.1700

Data Index: 8395381 (Open Web Text)

Max Activating Token Index: 944

Text #1

Max Range: 5.2570. Min Range: -5.2570

Max Act: 5.1907. Min Act: -0.1700

Data Index: 3363087 (Open Web Text)

Max Activating Token Index: 431

Text #2

Max Range: 5.2570. Min Range: -5.2570

Max Act: 5.1007. Min Act: -0.1700

Data Index: 2599414 (Open Web Text)

Max Activating Token Index: 489

Text #3

Max Range: 5.2570. Min Range: -5.2570

Max Act: 5.1506. Min Act: -0.1700

Data Index: 947775 (Open Web Text)

Max Activating Token Index: 996

Text #4

Max Range: 5.2570. Min Range: -5.2570

Max Act: 5.0357. Min Act: -0.1700

Data Index: 3693323 (Open Web Text)

Max Activating Token Index: 274

Text #5

Max Range: 5.2570. Min Range: -5.2570

Max Act: 5.0388. Min Act: -0.1700

Data Index: 3441078 (Open Web Text)

Max Activating Token Index: 598

Text #6

Max Range: 5.2570. Min Range: -5.2570

Max Act: 4.9767. Min Act: -0.1700

Data Index: 6075204 (Open Web Text)

Max Activating Token Index: 666

Text #7

Max Range: 5.2570. Min Range: -5.2570

Max Act: 4.9968. Min Act: -0.1700

Data Index: 2118581 (Open Web Text)

Max Activating Token Index: 350

Text #8

Max Range: 5.2570. Min Range: -5.2570

Max Act: 4.9501. Min Act: -0.1700

Data Index: 5306759 (Open Web Text)

Max Activating Token Index: 685

Text #9

Max Range: 5.2570. Min Range: -5.2570

Max Act: 4.9316. Min Act: -0.1700

Data Index: 3243779 (Open Web Text)

Max Activating Token Index: 372

Text #10

Max Range: 5.2570. Min Range: -5.2570

Max Act: 4.8612. Min Act: -0.1700

Data Index: 3838746 (Open Web Text)

Max Activating Token Index: 943

Text #11

Max Range: 5.2570. Min Range: -5.2570

Max Act: 4.8992. Min Act: -0.1700

Data Index: 504547 (Open Web Text)

Max Activating Token Index: 810

Text #12

Max Range: 5.2570. Min Range: -5.2570

Max Act: 4.9015. Min Act: -0.1700

Data Index: 860897 (Open Web Text)

Max Activating Token Index: 446

Text #13

Max Range: 5.2570. Min Range: -5.2570

Max Act: 4.8599. Min Act: -0.1700

Data Index: 894016 (Open Web Text)

Max Activating Token Index: 889

Text #14

Max Range: 5.2570. Min Range: -5.2570

Max Act: 4.8791. Min Act: -0.1700

Data Index: 5368525 (Open Web Text)

Max Activating Token Index: 994

Text #15

Max Range: 5.2570. Min Range: -5.2570

Max Act: 4.8096. Min Act: -0.1700

Data Index: 5875881 (Open Web Text)

Max Activating Token Index: 881

Text #16

Max Range: 5.2570. Min Range: -5.2570

Max Act: 4.8012. Min Act: -0.1700

Data Index: 8150108 (Open Web Text)

Max Activating Token Index: 887

Text #17

Max Range: 5.2570. Min Range: -5.2570

Max Act: 4.8389. Min Act: -0.1700

Data Index: 1609527 (Open Web Text)

Max Activating Token Index: 528

Text #18

Max Range: 5.2570. Min Range: -5.2570

Max Act: 4.8281. Min Act: -0.1700

Data Index: 5056257 (Open Web Text)

Max Activating Token Index: 883

Text #19

Max Range: 5.2570. Min Range: -5.2570

Max Act: 4.8345. Min Act: -0.1700

Data Index: 3355425 (Open Web Text)

Max Activating Token Index: 480