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

Dataset: Open Web Text

Neuron 631 in Layer 1

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: 3.2500. Min Range: -3.2500

Max Act: 3.2500. Min Act: -0.1700

Data Index: 7853674 (Open Web Text)

Max Activating Token Index: 121

Text #1

Max Range: 3.2500. Min Range: -3.2500

Max Act: 3.2129. Min Act: -0.1700

Data Index: 4723969 (Open Web Text)

Max Activating Token Index: 208

Text #2

Max Range: 3.2500. Min Range: -3.2500

Max Act: 3.1843. Min Act: -0.1700

Data Index: 4723962 (Open Web Text)

Max Activating Token Index: 553

Text #3

Max Range: 3.2500. Min Range: -3.2500

Max Act: 3.1780. Min Act: -0.1700

Data Index: 2406120 (Open Web Text)

Max Activating Token Index: 532

Text #4

Max Range: 3.2500. Min Range: -3.2500

Max Act: 3.1861. Min Act: -0.1700

Data Index: 7778747 (Open Web Text)

Max Activating Token Index: 95

Text #5

Max Range: 3.2500. Min Range: -3.2500

Max Act: 3.1805. Min Act: -0.1700

Data Index: 5243136 (Open Web Text)

Max Activating Token Index: 697

Text #6

Max Range: 3.2500. Min Range: -3.2500

Max Act: 3.1891. Min Act: -0.1700

Data Index: 3095600 (Open Web Text)

Max Activating Token Index: 773

Text #7

Max Range: 3.2500. Min Range: -3.2500

Max Act: 3.1616. Min Act: -0.1700

Data Index: 7044219 (Open Web Text)

Max Activating Token Index: 529

Text #8

Max Range: 3.2500. Min Range: -3.2500

Max Act: 3.1650. Min Act: -0.1700

Data Index: 2396746 (Open Web Text)

Max Activating Token Index: 651

Text #9

Max Range: 3.2500. Min Range: -3.2500

Max Act: 3.1704. Min Act: -0.1700

Data Index: 4723971 (Open Web Text)

Max Activating Token Index: 794

Text #10

Max Range: 3.2500. Min Range: -3.2500

Max Act: 3.1752. Min Act: -0.1700

Data Index: 3032000 (Open Web Text)

Max Activating Token Index: 1000

Text #11

Max Range: 3.2500. Min Range: -3.2500

Max Act: 3.1678. Min Act: -0.1700

Data Index: 5412672 (Open Web Text)

Max Activating Token Index: 283

Text #12

Max Range: 3.2500. Min Range: -3.2500

Max Act: 3.1502. Min Act: -0.1700

Data Index: 2703752 (Open Web Text)

Max Activating Token Index: 322

Text #13

Max Range: 3.2500. Min Range: -3.2500

Max Act: 3.1485. Min Act: -0.1700

Data Index: 4626584 (Open Web Text)

Max Activating Token Index: 458

Text #14

Max Range: 3.2500. Min Range: -3.2500

Max Act: 3.1478. Min Act: -0.1700

Data Index: 845405 (Open Web Text)

Max Activating Token Index: 336

Text #15

Max Range: 3.2500. Min Range: -3.2500

Max Act: 3.1543. Min Act: -0.1700

Data Index: 71243 (Open Web Text)

Max Activating Token Index: 179

Text #16

Max Range: 3.2500. Min Range: -3.2500

Max Act: 3.1409. Min Act: -0.1700

Data Index: 8109718 (Open Web Text)

Max Activating Token Index: 333

Text #17

Max Range: 3.2500. Min Range: -3.2500

Max Act: 3.1570. Min Act: -0.1700

Data Index: 7624099 (Open Web Text)

Max Activating Token Index: 706

Text #18

Max Range: 3.2500. Min Range: -3.2500

Max Act: 3.1489. Min Act: -0.1700

Data Index: 6932554 (Open Web Text)

Max Activating Token Index: 192

Text #19

Max Range: 3.2500. Min Range: -3.2500

Max Act: 3.1435. Min Act: -0.1700

Data Index: 5829544 (Open Web Text)

Max Activating Token Index: 51