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

Dataset: Open Web Text

Neuron 1689 in Layer 4

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: 3.7016. Min Range: -3.7016

Max Act: 3.6850. Min Act: -0.1700

Data Index: 4668850 (Open Web Text)

Max Activating Token Index: 503

Text #1

Max Range: 3.7016. Min Range: -3.7016

Max Act: 3.7016. Min Act: -0.1700

Data Index: 927252 (Open Web Text)

Max Activating Token Index: 558

Text #2

Max Range: 3.7016. Min Range: -3.7016

Max Act: 3.6945. Min Act: -0.1700

Data Index: 5899500 (Open Web Text)

Max Activating Token Index: 950

Text #3

Max Range: 3.7016. Min Range: -3.7016

Max Act: 3.6825. Min Act: -0.1700

Data Index: 6117000 (Open Web Text)

Max Activating Token Index: 652

Text #4

Max Range: 3.7016. Min Range: -3.7016

Max Act: 3.6583. Min Act: -0.1700

Data Index: 5889907 (Open Web Text)

Max Activating Token Index: 640

Text #5

Max Range: 3.7016. Min Range: -3.7016

Max Act: 3.6421. Min Act: -0.1700

Data Index: 8809453 (Open Web Text)

Max Activating Token Index: 525

Text #6

Max Range: 3.7016. Min Range: -3.7016

Max Act: 3.6458. Min Act: -0.1700

Data Index: 1455794 (Open Web Text)

Max Activating Token Index: 652

Text #7

Max Range: 3.7016. Min Range: -3.7016

Max Act: 3.6447. Min Act: -0.1700

Data Index: 6780370 (Open Web Text)

Max Activating Token Index: 412

Text #8

Max Range: 3.7016. Min Range: -3.7016

Max Act: 3.6445. Min Act: -0.1700

Data Index: 6181686 (Open Web Text)

Max Activating Token Index: 510

Text #9

Max Range: 3.7016. Min Range: -3.7016

Max Act: 3.6399. Min Act: -0.1700

Data Index: 3772647 (Open Web Text)

Max Activating Token Index: 672

Text #10

Max Range: 3.7016. Min Range: -3.7016

Max Act: 3.6428. Min Act: -0.1700

Data Index: 5395409 (Open Web Text)

Max Activating Token Index: 696

Text #11

Max Range: 3.7016. Min Range: -3.7016

Max Act: 3.6364. Min Act: -0.1700

Data Index: 1261437 (Open Web Text)

Max Activating Token Index: 777

Text #12

Max Range: 3.7016. Min Range: -3.7016

Max Act: 3.6445. Min Act: -0.1700

Data Index: 7383931 (Open Web Text)

Max Activating Token Index: 877

Text #13

Max Range: 3.7016. Min Range: -3.7016

Max Act: 3.6330. Min Act: -0.1700

Data Index: 7799596 (Open Web Text)

Max Activating Token Index: 494

Text #14

Max Range: 3.7016. Min Range: -3.7016

Max Act: 3.6254. Min Act: -0.1700

Data Index: 1113837 (Open Web Text)

Max Activating Token Index: 861

Text #15

Max Range: 3.7016. Min Range: -3.7016

Max Act: 3.6211. Min Act: -0.1700

Data Index: 3142253 (Open Web Text)

Max Activating Token Index: 959

Text #16

Max Range: 3.7016. Min Range: -3.7016

Max Act: 3.6368. Min Act: -0.1700

Data Index: 3775608 (Open Web Text)

Max Activating Token Index: 67

Text #17

Max Range: 3.7016. Min Range: -3.7016

Max Act: 3.6212. Min Act: -0.1700

Data Index: 6959161 (Open Web Text)

Max Activating Token Index: 769

Text #18

Max Range: 3.7016. Min Range: -3.7016

Max Act: 3.6066. Min Act: -0.1700

Data Index: 1512777 (Open Web Text)

Max Activating Token Index: 751

Text #19

Max Range: 3.7016. Min Range: -3.7016

Max Act: 3.6238. Min Act: -0.1700

Data Index: 5627095 (Open Web Text)

Max Activating Token Index: 238