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

Dataset: Open Web Text

Neuron 1225 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: 3.2391. Min Range: -3.2391

Max Act: 3.2391. Min Act: -0.1700

Data Index: 2648721 (Open Web Text)

Max Activating Token Index: 83

Text #1

Max Range: 3.2391. Min Range: -3.2391

Max Act: 3.2279. Min Act: -0.1700

Data Index: 5187069 (Open Web Text)

Max Activating Token Index: 68

Text #2

Max Range: 3.2391. Min Range: -3.2391

Max Act: 3.2251. Min Act: -0.1700

Data Index: 275307 (Open Web Text)

Max Activating Token Index: 13

Text #3

Max Range: 3.2391. Min Range: -3.2391

Max Act: 3.2207. Min Act: -0.1700

Data Index: 5267108 (Open Web Text)

Max Activating Token Index: 47

Text #4

Max Range: 3.2391. Min Range: -3.2391

Max Act: 3.1936. Min Act: -0.1700

Data Index: 6837145 (Open Web Text)

Max Activating Token Index: 661

Text #5

Max Range: 3.2391. Min Range: -3.2391

Max Act: 3.1938. Min Act: -0.1700

Data Index: 131919 (Open Web Text)

Max Activating Token Index: 32

Text #6

Max Range: 3.2391. Min Range: -3.2391

Max Act: 3.2056. Min Act: -0.1700

Data Index: 941912 (Open Web Text)

Max Activating Token Index: 7

Text #7

Max Range: 3.2391. Min Range: -3.2391

Max Act: 3.2084. Min Act: -0.1700

Data Index: 40381 (Open Web Text)

Max Activating Token Index: 59

Text #8

Max Range: 3.2391. Min Range: -3.2391

Max Act: 3.1874. Min Act: -0.1700

Data Index: 4392628 (Open Web Text)

Max Activating Token Index: 34

Text #9

Max Range: 3.2391. Min Range: -3.2391

Max Act: 3.1607. Min Act: -0.1700

Data Index: 1019623 (Open Web Text)

Max Activating Token Index: 880

Text #10

Max Range: 3.2391. Min Range: -3.2391

Max Act: 3.1664. Min Act: -0.1700

Data Index: 1770251 (Open Web Text)

Max Activating Token Index: 63

Text #11

Max Range: 3.2391. Min Range: -3.2391

Max Act: 3.1510. Min Act: -0.1700

Data Index: 637627 (Open Web Text)

Max Activating Token Index: 828

Text #12

Max Range: 3.2391. Min Range: -3.2391

Max Act: 3.1559. Min Act: -0.1700

Data Index: 5209136 (Open Web Text)

Max Activating Token Index: 840

Text #13

Max Range: 3.2391. Min Range: -3.2391

Max Act: 3.1500. Min Act: -0.1700

Data Index: 6071125 (Open Web Text)

Max Activating Token Index: 844

Text #14

Max Range: 3.2391. Min Range: -3.2391

Max Act: 3.1402. Min Act: -0.1700

Data Index: 6114834 (Open Web Text)

Max Activating Token Index: 965

Text #15

Max Range: 3.2391. Min Range: -3.2391

Max Act: 3.1331. Min Act: -0.1700

Data Index: 6551492 (Open Web Text)

Max Activating Token Index: 694

Text #16

Max Range: 3.2391. Min Range: -3.2391

Max Act: 3.1474. Min Act: -0.1700

Data Index: 952733 (Open Web Text)

Max Activating Token Index: 505

Text #17

Max Range: 3.2391. Min Range: -3.2391

Max Act: 3.1302. Min Act: -0.1700

Data Index: 3221758 (Open Web Text)

Max Activating Token Index: 744

Text #18

Max Range: 3.2391. Min Range: -3.2391

Max Act: 3.1604. Min Act: -0.1700

Data Index: 6864745 (Open Web Text)

Max Activating Token Index: 393

Text #19

Max Range: 3.2391. Min Range: -3.2391

Max Act: 3.1623. Min Act: -0.1700

Data Index: 117011 (Open Web Text)

Max Activating Token Index: 841