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

Dataset: Open Web Text

Neuron 2417 in Layer 4

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: 3.2252. Min Range: -3.2252

Max Act: 3.2252. Min Act: -0.1700

Data Index: 6889447 (Open Web Text)

Max Activating Token Index: 693

Text #1

Max Range: 3.2252. Min Range: -3.2252

Max Act: 3.1520. Min Act: -0.1700

Data Index: 3783118 (Open Web Text)

Max Activating Token Index: 291

Text #2

Max Range: 3.2252. Min Range: -3.2252

Max Act: 3.1513. Min Act: -0.1700

Data Index: 8310317 (Open Web Text)

Max Activating Token Index: 601

Text #3

Max Range: 3.2252. Min Range: -3.2252

Max Act: 3.1384. Min Act: -0.1700

Data Index: 127800 (Open Web Text)

Max Activating Token Index: 448

Text #4

Max Range: 3.2252. Min Range: -3.2252

Max Act: 3.1532. Min Act: -0.1700

Data Index: 1296453 (Open Web Text)

Max Activating Token Index: 938

Text #5

Max Range: 3.2252. Min Range: -3.2252

Max Act: 3.1592. Min Act: -0.1700

Data Index: 2725690 (Open Web Text)

Max Activating Token Index: 967

Text #6

Max Range: 3.2252. Min Range: -3.2252

Max Act: 3.1238. Min Act: -0.1700

Data Index: 2629909 (Open Web Text)

Max Activating Token Index: 820

Text #7

Max Range: 3.2252. Min Range: -3.2252

Max Act: 3.1630. Min Act: -0.1700

Data Index: 8185586 (Open Web Text)

Max Activating Token Index: 495

Text #8

Max Range: 3.2252. Min Range: -3.2252

Max Act: 3.1530. Min Act: -0.1700

Data Index: 4952420 (Open Web Text)

Max Activating Token Index: 671

Text #9

Max Range: 3.2252. Min Range: -3.2252

Max Act: 3.1330. Min Act: -0.1700

Data Index: 5602424 (Open Web Text)

Max Activating Token Index: 834

Text #10

Max Range: 3.2252. Min Range: -3.2252

Max Act: 3.1382. Min Act: -0.1700

Data Index: 1866032 (Open Web Text)

Max Activating Token Index: 734

Text #11

Max Range: 3.2252. Min Range: -3.2252

Max Act: 3.1050. Min Act: -0.1700

Data Index: 5241735 (Open Web Text)

Max Activating Token Index: 556

Text #12

Max Range: 3.2252. Min Range: -3.2252

Max Act: 3.0712. Min Act: -0.1700

Data Index: 523311 (Open Web Text)

Max Activating Token Index: 648

Text #13

Max Range: 3.2252. Min Range: -3.2252

Max Act: 3.0729. Min Act: -0.1700

Data Index: 5917706 (Open Web Text)

Max Activating Token Index: 590

Text #14

Max Range: 3.2252. Min Range: -3.2252

Max Act: 3.0876. Min Act: -0.1700

Data Index: 7864583 (Open Web Text)

Max Activating Token Index: 207

Text #15

Max Range: 3.2252. Min Range: -3.2252

Max Act: 3.0849. Min Act: -0.1700

Data Index: 8582333 (Open Web Text)

Max Activating Token Index: 47

Text #16

Max Range: 3.2252. Min Range: -3.2252

Max Act: 3.0882. Min Act: -0.1700

Data Index: 6515647 (Open Web Text)

Max Activating Token Index: 222

Text #17

Max Range: 3.2252. Min Range: -3.2252

Max Act: 3.0744. Min Act: -0.1700

Data Index: 1211065 (Open Web Text)

Max Activating Token Index: 775

Text #18

Max Range: 3.2252. Min Range: -3.2252

Max Act: 3.0816. Min Act: -0.1700

Data Index: 7767502 (Open Web Text)

Max Activating Token Index: 768

Text #19

Max Range: 3.2252. Min Range: -3.2252

Max Act: 3.0551. Min Act: -0.1700

Data Index: 3728228 (Open Web Text)

Max Activating Token Index: 570