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

Dataset: Open Web Text

Neuron 2328 in Layer 0

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: 1.7296. Min Range: -1.7296

Max Act: 1.7296. Min Act: -0.1700

Data Index: 8219381 (Open Web Text)

Max Activating Token Index: 821

Text #1

Max Range: 1.7296. Min Range: -1.7296

Max Act: 1.7207. Min Act: -0.1695

Data Index: 7461136 (Open Web Text)

Max Activating Token Index: 596

Text #2

Max Range: 1.7296. Min Range: -1.7296

Max Act: 1.6922. Min Act: -0.1687

Data Index: 1628057 (Open Web Text)

Max Activating Token Index: 1007

Text #3

Max Range: 1.7296. Min Range: -1.7296

Max Act: 1.6861. Min Act: -0.1690

Data Index: 8021869 (Open Web Text)

Max Activating Token Index: 31

Text #4

Max Range: 1.7296. Min Range: -1.7296

Max Act: 1.6831. Min Act: -0.1700

Data Index: 3731589 (Open Web Text)

Max Activating Token Index: 662

Text #5

Max Range: 1.7296. Min Range: -1.7296

Max Act: 1.6819. Min Act: -0.1682

Data Index: 2029859 (Open Web Text)

Max Activating Token Index: 1008

Text #6

Max Range: 1.7296. Min Range: -1.7296

Max Act: 1.6752. Min Act: -0.1699

Data Index: 7139061 (Open Web Text)

Max Activating Token Index: 513

Text #7

Max Range: 1.7296. Min Range: -1.7296

Max Act: 1.6758. Min Act: -0.1680

Data Index: 6511528 (Open Web Text)

Max Activating Token Index: 463

Text #8

Max Range: 1.7296. Min Range: -1.7296

Max Act: 1.6825. Min Act: -0.1691

Data Index: 5539672 (Open Web Text)

Max Activating Token Index: 83

Text #9

Max Range: 1.7296. Min Range: -1.7296

Max Act: 1.6773. Min Act: -0.1700

Data Index: 5968313 (Open Web Text)

Max Activating Token Index: 15

Text #10

Max Range: 1.7296. Min Range: -1.7296

Max Act: 1.6699. Min Act: -0.1698

Data Index: 7039116 (Open Web Text)

Max Activating Token Index: 770

Text #11

Max Range: 1.7296. Min Range: -1.7296

Max Act: 1.6635. Min Act: -0.1599

Data Index: 450776 (Open Web Text)

Max Activating Token Index: 9

Text #12

Max Range: 1.7296. Min Range: -1.7296

Max Act: 1.6686. Min Act: -0.1691

Data Index: 7699018 (Open Web Text)

Max Activating Token Index: 721

Text #13

Max Range: 1.7296. Min Range: -1.7296

Max Act: 1.6684. Min Act: -0.1549

Data Index: 4548337 (Open Web Text)

Max Activating Token Index: 810

Text #14

Max Range: 1.7296. Min Range: -1.7296

Max Act: 1.6615. Min Act: -0.1574

Data Index: 5090880 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 1.7296. Min Range: -1.7296

Max Act: 1.6559. Min Act: -0.1700

Data Index: 8651370 (Open Web Text)

Max Activating Token Index: 543

Text #16

Max Range: 1.7296. Min Range: -1.7296

Max Act: 1.6587. Min Act: -0.1582

Data Index: 5481091 (Open Web Text)

Max Activating Token Index: 200

Text #17

Max Range: 1.7296. Min Range: -1.7296

Max Act: 1.6600. Min Act: -0.1700

Data Index: 433829 (Open Web Text)

Max Activating Token Index: 96

Text #18

Max Range: 1.7296. Min Range: -1.7296

Max Act: 1.6464. Min Act: -0.1575

Data Index: 402610 (Open Web Text)

Max Activating Token Index: 931

Text #19

Max Range: 1.7296. Min Range: -1.7296

Max Act: 1.6530. Min Act: -0.1700

Data Index: 417861 (Open Web Text)

Max Activating Token Index: 117