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

Dataset: Open Web Text

Neuron 2438 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: 4.5976. Min Range: -4.5976

Max Act: 4.5976. Min Act: -0.1700

Data Index: 8693235 (Open Web Text)

Max Activating Token Index: 466

Text #1

Max Range: 4.5976. Min Range: -4.5976

Max Act: 4.5140. Min Act: -0.1700

Data Index: 3606439 (Open Web Text)

Max Activating Token Index: 647

Text #2

Max Range: 4.5976. Min Range: -4.5976

Max Act: 4.5826. Min Act: -0.1700

Data Index: 5217893 (Open Web Text)

Max Activating Token Index: 753

Text #3

Max Range: 4.5976. Min Range: -4.5976

Max Act: 4.5235. Min Act: -0.1700

Data Index: 3592405 (Open Web Text)

Max Activating Token Index: 780

Text #4

Max Range: 4.5976. Min Range: -4.5976

Max Act: 4.4906. Min Act: -0.1700

Data Index: 1929018 (Open Web Text)

Max Activating Token Index: 911

Text #5

Max Range: 4.5976. Min Range: -4.5976

Max Act: 4.4568. Min Act: -0.1700

Data Index: 5916184 (Open Web Text)

Max Activating Token Index: 161

Text #6

Max Range: 4.5976. Min Range: -4.5976

Max Act: 4.4245. Min Act: -0.1700

Data Index: 1386922 (Open Web Text)

Max Activating Token Index: 225

Text #7

Max Range: 4.5976. Min Range: -4.5976

Max Act: 4.4451. Min Act: -0.1700

Data Index: 849481 (Open Web Text)

Max Activating Token Index: 710

Text #8

Max Range: 4.5976. Min Range: -4.5976

Max Act: 4.4243. Min Act: -0.1700

Data Index: 1695959 (Open Web Text)

Max Activating Token Index: 276

Text #9

Max Range: 4.5976. Min Range: -4.5976

Max Act: 4.4292. Min Act: -0.1700

Data Index: 2691601 (Open Web Text)

Max Activating Token Index: 426

Text #10

Max Range: 4.5976. Min Range: -4.5976

Max Act: 4.4466. Min Act: -0.1700

Data Index: 7057871 (Open Web Text)

Max Activating Token Index: 432

Text #11

Max Range: 4.5976. Min Range: -4.5976

Max Act: 4.3797. Min Act: -0.1700

Data Index: 2374904 (Open Web Text)

Max Activating Token Index: 799

Text #12

Max Range: 4.5976. Min Range: -4.5976

Max Act: 4.4452. Min Act: -0.1700

Data Index: 7516570 (Open Web Text)

Max Activating Token Index: 152

Text #13

Max Range: 4.5976. Min Range: -4.5976

Max Act: 4.3722. Min Act: -0.1700

Data Index: 1180462 (Open Web Text)

Max Activating Token Index: 456

Text #14

Max Range: 4.5976. Min Range: -4.5976

Max Act: 4.3776. Min Act: -0.1700

Data Index: 8238547 (Open Web Text)

Max Activating Token Index: 379

Text #15

Max Range: 4.5976. Min Range: -4.5976

Max Act: 4.3869. Min Act: -0.1700

Data Index: 8349148 (Open Web Text)

Max Activating Token Index: 487

Text #16

Max Range: 4.5976. Min Range: -4.5976

Max Act: 4.3412. Min Act: -0.1700

Data Index: 8518553 (Open Web Text)

Max Activating Token Index: 581

Text #17

Max Range: 4.5976. Min Range: -4.5976

Max Act: 4.3408. Min Act: -0.1700

Data Index: 1355381 (Open Web Text)

Max Activating Token Index: 199

Text #18

Max Range: 4.5976. Min Range: -4.5976

Max Act: 4.3874. Min Act: -0.1700

Data Index: 2179451 (Open Web Text)

Max Activating Token Index: 453

Text #19

Max Range: 4.5976. Min Range: -4.5976

Max Act: 4.3912. Min Act: -0.1700

Data Index: 6399814 (Open Web Text)

Max Activating Token Index: 980