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

Dataset: Open Web Text

Neuron 1551 in Layer 3

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: 5.1493. Min Range: -5.1493

Max Act: 5.1493. Min Act: -0.1700

Data Index: 8419430 (Open Web Text)

Max Activating Token Index: 973

Text #1

Max Range: 5.1493. Min Range: -5.1493

Max Act: 5.0501. Min Act: -0.1700

Data Index: 2255953 (Open Web Text)

Max Activating Token Index: 886

Text #2

Max Range: 5.1493. Min Range: -5.1493

Max Act: 5.0309. Min Act: -0.1700

Data Index: 481221 (Open Web Text)

Max Activating Token Index: 24

Text #3

Max Range: 5.1493. Min Range: -5.1493

Max Act: 5.0734. Min Act: -0.1693

Data Index: 3193392 (Open Web Text)

Max Activating Token Index: 263

Text #4

Max Range: 5.1493. Min Range: -5.1493

Max Act: 4.9843. Min Act: -0.1700

Data Index: 6167955 (Open Web Text)

Max Activating Token Index: 603

Text #5

Max Range: 5.1493. Min Range: -5.1493

Max Act: 4.9568. Min Act: -0.1700

Data Index: 7472219 (Open Web Text)

Max Activating Token Index: 947

Text #6

Max Range: 5.1493. Min Range: -5.1493

Max Act: 5.0074. Min Act: -0.1700

Data Index: 5990712 (Open Web Text)

Max Activating Token Index: 8

Text #7

Max Range: 5.1493. Min Range: -5.1493

Max Act: 4.9705. Min Act: -0.1700

Data Index: 1291196 (Open Web Text)

Max Activating Token Index: 877

Text #8

Max Range: 5.1493. Min Range: -5.1493

Max Act: 4.9504. Min Act: -0.1700

Data Index: 3526588 (Open Web Text)

Max Activating Token Index: 879

Text #9

Max Range: 5.1493. Min Range: -5.1493

Max Act: 4.9818. Min Act: -0.1700

Data Index: 3354711 (Open Web Text)

Max Activating Token Index: 11

Text #10

Max Range: 5.1493. Min Range: -5.1493

Max Act: 5.0376. Min Act: -0.1700

Data Index: 4610386 (Open Web Text)

Max Activating Token Index: 22

Text #11

Max Range: 5.1493. Min Range: -5.1493

Max Act: 4.9755. Min Act: -0.1700

Data Index: 8167945 (Open Web Text)

Max Activating Token Index: 428

Text #12

Max Range: 5.1493. Min Range: -5.1493

Max Act: 4.9391. Min Act: -0.1700

Data Index: 7747825 (Open Web Text)

Max Activating Token Index: 885

Text #13

Max Range: 5.1493. Min Range: -5.1493

Max Act: 4.9609. Min Act: -0.1700

Data Index: 5956075 (Open Web Text)

Max Activating Token Index: 513

Text #14

Max Range: 5.1493. Min Range: -5.1493

Max Act: 4.9924. Min Act: -0.1698

Data Index: 1336760 (Open Web Text)

Max Activating Token Index: 834

Text #15

Max Range: 5.1493. Min Range: -5.1493

Max Act: 4.9774. Min Act: -0.1700

Data Index: 8159260 (Open Web Text)

Max Activating Token Index: 152

Text #16

Max Range: 5.1493. Min Range: -5.1493

Max Act: 4.9717. Min Act: -0.1700

Data Index: 5761996 (Open Web Text)

Max Activating Token Index: 321

Text #17

Max Range: 5.1493. Min Range: -5.1493

Max Act: 4.9369. Min Act: -0.1700

Data Index: 7265531 (Open Web Text)

Max Activating Token Index: 915

Text #18

Max Range: 5.1493. Min Range: -5.1493

Max Act: 4.9165. Min Act: -0.1700

Data Index: 5641391 (Open Web Text)

Max Activating Token Index: 852

Text #19

Max Range: 5.1493. Min Range: -5.1493

Max Act: 4.9005. Min Act: -0.1700

Data Index: 7003796 (Open Web Text)

Max Activating Token Index: 146