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

Dataset: Open Web Text

Neuron 1003 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: 6.0186. Min Range: -6.0186

Max Act: 6.0186. Min Act: -0.1700

Data Index: 8149157 (Open Web Text)

Max Activating Token Index: 611

Text #1

Max Range: 6.0186. Min Range: -6.0186

Max Act: 5.8802. Min Act: -0.1700

Data Index: 3084867 (Open Web Text)

Max Activating Token Index: 89

Text #2

Max Range: 6.0186. Min Range: -6.0186

Max Act: 5.8617. Min Act: -0.1700

Data Index: 427148 (Open Web Text)

Max Activating Token Index: 942

Text #3

Max Range: 6.0186. Min Range: -6.0186

Max Act: 5.8439. Min Act: -0.1700

Data Index: 4267932 (Open Web Text)

Max Activating Token Index: 730

Text #4

Max Range: 6.0186. Min Range: -6.0186

Max Act: 5.7655. Min Act: -0.1700

Data Index: 8298366 (Open Web Text)

Max Activating Token Index: 893

Text #5

Max Range: 6.0186. Min Range: -6.0186

Max Act: 5.8242. Min Act: -0.1700

Data Index: 5573150 (Open Web Text)

Max Activating Token Index: 251

Text #6

Max Range: 6.0186. Min Range: -6.0186

Max Act: 5.7515. Min Act: -0.1700

Data Index: 8442366 (Open Web Text)

Max Activating Token Index: 981

Text #7

Max Range: 6.0186. Min Range: -6.0186

Max Act: 5.7322. Min Act: -0.1700

Data Index: 7256924 (Open Web Text)

Max Activating Token Index: 907

Text #8

Max Range: 6.0186. Min Range: -6.0186

Max Act: 5.7433. Min Act: -0.1700

Data Index: 928208 (Open Web Text)

Max Activating Token Index: 586

Text #9

Max Range: 6.0186. Min Range: -6.0186

Max Act: 5.7591. Min Act: -0.1700

Data Index: 1891078 (Open Web Text)

Max Activating Token Index: 648

Text #10

Max Range: 6.0186. Min Range: -6.0186

Max Act: 5.7256. Min Act: -0.1700

Data Index: 7941287 (Open Web Text)

Max Activating Token Index: 501

Text #11

Max Range: 6.0186. Min Range: -6.0186

Max Act: 5.6795. Min Act: -0.1700

Data Index: 760116 (Open Web Text)

Max Activating Token Index: 100

Text #12

Max Range: 6.0186. Min Range: -6.0186

Max Act: 5.7164. Min Act: -0.1700

Data Index: 3366673 (Open Web Text)

Max Activating Token Index: 244

Text #13

Max Range: 6.0186. Min Range: -6.0186

Max Act: 5.6469. Min Act: -0.1700

Data Index: 5401957 (Open Web Text)

Max Activating Token Index: 438

Text #14

Max Range: 6.0186. Min Range: -6.0186

Max Act: 5.6437. Min Act: -0.1700

Data Index: 5648056 (Open Web Text)

Max Activating Token Index: 907

Text #15

Max Range: 6.0186. Min Range: -6.0186

Max Act: 5.6882. Min Act: -0.1700

Data Index: 5047633 (Open Web Text)

Max Activating Token Index: 704

Text #16

Max Range: 6.0186. Min Range: -6.0186

Max Act: 5.6212. Min Act: -0.1700

Data Index: 4987845 (Open Web Text)

Max Activating Token Index: 914

Text #17

Max Range: 6.0186. Min Range: -6.0186

Max Act: 5.6600. Min Act: -0.1700

Data Index: 6902019 (Open Web Text)

Max Activating Token Index: 642

Text #18

Max Range: 6.0186. Min Range: -6.0186

Max Act: 5.6504. Min Act: -0.1700

Data Index: 7861388 (Open Web Text)

Max Activating Token Index: 533

Text #19

Max Range: 6.0186. Min Range: -6.0186

Max Act: 5.6428. Min Act: -0.1700

Data Index: 4509249 (Open Web Text)

Max Activating Token Index: 963