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

Dataset: Open Web Text

Neuron 867 in Layer 5

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: 2.8577. Min Range: -2.8577

Max Act: 2.8335. Min Act: -0.1700

Data Index: 8175681 (Open Web Text)

Max Activating Token Index: 561

Text #1

Max Range: 2.8577. Min Range: -2.8577

Max Act: 2.8294. Min Act: -0.1700

Data Index: 7219276 (Open Web Text)

Max Activating Token Index: 177

Text #2

Max Range: 2.8577. Min Range: -2.8577

Max Act: 2.7814. Min Act: -0.1700

Data Index: 5573999 (Open Web Text)

Max Activating Token Index: 692

Text #3

Max Range: 2.8577. Min Range: -2.8577

Max Act: 2.8129. Min Act: -0.1700

Data Index: 2731746 (Open Web Text)

Max Activating Token Index: 542

Text #4

Max Range: 2.8577. Min Range: -2.8577

Max Act: 2.8577. Min Act: -0.1700

Data Index: 3819571 (Open Web Text)

Max Activating Token Index: 581

Text #5

Max Range: 2.8577. Min Range: -2.8577

Max Act: 2.8094. Min Act: -0.1700

Data Index: 8464583 (Open Web Text)

Max Activating Token Index: 603

Text #6

Max Range: 2.8577. Min Range: -2.8577

Max Act: 2.8301. Min Act: -0.1700

Data Index: 1296946 (Open Web Text)

Max Activating Token Index: 521

Text #7

Max Range: 2.8577. Min Range: -2.8577

Max Act: 2.7749. Min Act: -0.1700

Data Index: 2805163 (Open Web Text)

Max Activating Token Index: 344

Text #8

Max Range: 2.8577. Min Range: -2.8577

Max Act: 2.7924. Min Act: -0.1700

Data Index: 1807232 (Open Web Text)

Max Activating Token Index: 201

Text #9

Max Range: 2.8577. Min Range: -2.8577

Max Act: 2.7716. Min Act: -0.1700

Data Index: 4029864 (Open Web Text)

Max Activating Token Index: 249

Text #10

Max Range: 2.8577. Min Range: -2.8577

Max Act: 2.7547. Min Act: -0.1700

Data Index: 1233926 (Open Web Text)

Max Activating Token Index: 484

Text #11

Max Range: 2.8577. Min Range: -2.8577

Max Act: 2.7469. Min Act: -0.1700

Data Index: 4250297 (Open Web Text)

Max Activating Token Index: 779

Text #12

Max Range: 2.8577. Min Range: -2.8577

Max Act: 2.7385. Min Act: -0.1700

Data Index: 2684436 (Open Web Text)

Max Activating Token Index: 100

Text #13

Max Range: 2.8577. Min Range: -2.8577

Max Act: 2.7504. Min Act: -0.1700

Data Index: 4995237 (Open Web Text)

Max Activating Token Index: 587

Text #14

Max Range: 2.8577. Min Range: -2.8577

Max Act: 2.7495. Min Act: -0.1700

Data Index: 8628920 (Open Web Text)

Max Activating Token Index: 779

Text #15

Max Range: 2.8577. Min Range: -2.8577

Max Act: 2.7308. Min Act: -0.1700

Data Index: 5136855 (Open Web Text)

Max Activating Token Index: 275

Text #16

Max Range: 2.8577. Min Range: -2.8577

Max Act: 2.7578. Min Act: -0.1700

Data Index: 8064711 (Open Web Text)

Max Activating Token Index: 744

Text #17

Max Range: 2.8577. Min Range: -2.8577

Max Act: 2.7359. Min Act: -0.1700

Data Index: 4972394 (Open Web Text)

Max Activating Token Index: 598

Text #18

Max Range: 2.8577. Min Range: -2.8577

Max Act: 2.7183. Min Act: -0.1700

Data Index: 1912386 (Open Web Text)

Max Activating Token Index: 79

Text #19

Max Range: 2.8577. Min Range: -2.8577

Max Act: 2.6999. Min Act: -0.1700

Data Index: 6001957 (Open Web Text)

Max Activating Token Index: 201