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

Dataset: Open Web Text

Neuron 1707 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: 5.0465. Min Range: -5.0465

Max Act: 5.0465. Min Act: -0.1700

Data Index: 6071238 (Open Web Text)

Max Activating Token Index: 788

Text #1

Max Range: 5.0465. Min Range: -5.0465

Max Act: 4.9138. Min Act: -0.1700

Data Index: 2545373 (Open Web Text)

Max Activating Token Index: 532

Text #2

Max Range: 5.0465. Min Range: -5.0465

Max Act: 4.8687. Min Act: -0.1700

Data Index: 2741429 (Open Web Text)

Max Activating Token Index: 767

Text #3

Max Range: 5.0465. Min Range: -5.0465

Max Act: 4.8732. Min Act: -0.1700

Data Index: 4308609 (Open Web Text)

Max Activating Token Index: 815

Text #4

Max Range: 5.0465. Min Range: -5.0465

Max Act: 4.8697. Min Act: -0.1700

Data Index: 4019689 (Open Web Text)

Max Activating Token Index: 264

Text #5

Max Range: 5.0465. Min Range: -5.0465

Max Act: 4.8825. Min Act: -0.1700

Data Index: 4007493 (Open Web Text)

Max Activating Token Index: 1010

Text #6

Max Range: 5.0465. Min Range: -5.0465

Max Act: 4.8875. Min Act: -0.1700

Data Index: 7300081 (Open Web Text)

Max Activating Token Index: 770

Text #7

Max Range: 5.0465. Min Range: -5.0465

Max Act: 4.9078. Min Act: -0.1700

Data Index: 8741344 (Open Web Text)

Max Activating Token Index: 522

Text #8

Max Range: 5.0465. Min Range: -5.0465

Max Act: 4.8619. Min Act: -0.1700

Data Index: 2207022 (Open Web Text)

Max Activating Token Index: 322

Text #9

Max Range: 5.0465. Min Range: -5.0465

Max Act: 4.8387. Min Act: -0.1700

Data Index: 6560329 (Open Web Text)

Max Activating Token Index: 366

Text #10

Max Range: 5.0465. Min Range: -5.0465

Max Act: 4.8506. Min Act: -0.1700

Data Index: 5271639 (Open Web Text)

Max Activating Token Index: 644

Text #11

Max Range: 5.0465. Min Range: -5.0465

Max Act: 4.7973. Min Act: -0.1700

Data Index: 2813542 (Open Web Text)

Max Activating Token Index: 526

Text #12

Max Range: 5.0465. Min Range: -5.0465

Max Act: 4.7900. Min Act: -0.1700

Data Index: 4154881 (Open Web Text)

Max Activating Token Index: 336

Text #13

Max Range: 5.0465. Min Range: -5.0465

Max Act: 4.8015. Min Act: -0.1700

Data Index: 3935190 (Open Web Text)

Max Activating Token Index: 58

Text #14

Max Range: 5.0465. Min Range: -5.0465

Max Act: 4.8147. Min Act: -0.1700

Data Index: 3547650 (Open Web Text)

Max Activating Token Index: 666

Text #15

Max Range: 5.0465. Min Range: -5.0465

Max Act: 4.7883. Min Act: -0.1700

Data Index: 5301554 (Open Web Text)

Max Activating Token Index: 710

Text #16

Max Range: 5.0465. Min Range: -5.0465

Max Act: 4.8456. Min Act: -0.1700

Data Index: 4331566 (Open Web Text)

Max Activating Token Index: 434

Text #17

Max Range: 5.0465. Min Range: -5.0465

Max Act: 4.7759. Min Act: -0.1700

Data Index: 4768873 (Open Web Text)

Max Activating Token Index: 72

Text #18

Max Range: 5.0465. Min Range: -5.0465

Max Act: 4.8104. Min Act: -0.1700

Data Index: 4266698 (Open Web Text)

Max Activating Token Index: 444

Text #19

Max Range: 5.0465. Min Range: -5.0465

Max Act: 4.7783. Min Act: -0.1700

Data Index: 4270266 (Open Web Text)

Max Activating Token Index: 552