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

Dataset: Open Web Text

Neuron 307 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: 5.0620. Min Range: -5.0620

Max Act: 5.0620. Min Act: -0.1700

Data Index: 5058070 (Open Web Text)

Max Activating Token Index: 91

Text #1

Max Range: 5.0620. Min Range: -5.0620

Max Act: 4.9592. Min Act: -0.1700

Data Index: 7323341 (Open Web Text)

Max Activating Token Index: 660

Text #2

Max Range: 5.0620. Min Range: -5.0620

Max Act: 4.9760. Min Act: -0.1700

Data Index: 7285722 (Open Web Text)

Max Activating Token Index: 452

Text #3

Max Range: 5.0620. Min Range: -5.0620

Max Act: 4.9691. Min Act: -0.1700

Data Index: 6079644 (Open Web Text)

Max Activating Token Index: 126

Text #4

Max Range: 5.0620. Min Range: -5.0620

Max Act: 4.9358. Min Act: -0.1700

Data Index: 7138047 (Open Web Text)

Max Activating Token Index: 72

Text #5

Max Range: 5.0620. Min Range: -5.0620

Max Act: 4.9515. Min Act: -0.1700

Data Index: 5133905 (Open Web Text)

Max Activating Token Index: 56

Text #6

Max Range: 5.0620. Min Range: -5.0620

Max Act: 4.9513. Min Act: -0.1700

Data Index: 8139187 (Open Web Text)

Max Activating Token Index: 405

Text #7

Max Range: 5.0620. Min Range: -5.0620

Max Act: 4.9268. Min Act: -0.1700

Data Index: 4410167 (Open Web Text)

Max Activating Token Index: 175

Text #8

Max Range: 5.0620. Min Range: -5.0620

Max Act: 4.9012. Min Act: -0.1700

Data Index: 823538 (Open Web Text)

Max Activating Token Index: 725

Text #9

Max Range: 5.0620. Min Range: -5.0620

Max Act: 4.9160. Min Act: -0.1700

Data Index: 4185081 (Open Web Text)

Max Activating Token Index: 641

Text #10

Max Range: 5.0620. Min Range: -5.0620

Max Act: 4.9275. Min Act: -0.1700

Data Index: 1451297 (Open Web Text)

Max Activating Token Index: 536

Text #11

Max Range: 5.0620. Min Range: -5.0620

Max Act: 4.8907. Min Act: -0.1700

Data Index: 7379104 (Open Web Text)

Max Activating Token Index: 313

Text #12

Max Range: 5.0620. Min Range: -5.0620

Max Act: 4.9184. Min Act: -0.1700

Data Index: 6363477 (Open Web Text)

Max Activating Token Index: 453

Text #13

Max Range: 5.0620. Min Range: -5.0620

Max Act: 4.8625. Min Act: -0.1700

Data Index: 1925484 (Open Web Text)

Max Activating Token Index: 856

Text #14

Max Range: 5.0620. Min Range: -5.0620

Max Act: 4.8618. Min Act: -0.1700

Data Index: 4083539 (Open Web Text)

Max Activating Token Index: 38

Text #15

Max Range: 5.0620. Min Range: -5.0620

Max Act: 4.8621. Min Act: -0.1700

Data Index: 3876750 (Open Web Text)

Max Activating Token Index: 327

Text #16

Max Range: 5.0620. Min Range: -5.0620

Max Act: 4.8473. Min Act: -0.1700

Data Index: 8642622 (Open Web Text)

Max Activating Token Index: 95

Text #17

Max Range: 5.0620. Min Range: -5.0620

Max Act: 4.8556. Min Act: -0.1700

Data Index: 6996327 (Open Web Text)

Max Activating Token Index: 117

Text #18

Max Range: 5.0620. Min Range: -5.0620

Max Act: 4.8591. Min Act: -0.1700

Data Index: 6902680 (Open Web Text)

Max Activating Token Index: 62

Text #19

Max Range: 5.0620. Min Range: -5.0620

Max Act: 4.8563. Min Act: -0.1700

Data Index: 7069567 (Open Web Text)

Max Activating Token Index: 440