Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4960 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6605. Min Range: -4.6605
Max Act: 4.6605. Min Act: -0.1700
Data Index: 5499881 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6605. Min Range: -4.6605
Max Act: 4.5355. Min Act: -0.1700
Data Index: 7259773 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6605. Min Range: -4.6605
Max Act: 4.5355. Min Act: -0.1700
Data Index: 4837570 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6605. Min Range: -4.6605
Max Act: 4.5355. Min Act: -0.1700
Data Index: 3018395 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6605. Min Range: -4.6605
Max Act: 4.5042. Min Act: -0.1700
Data Index: 2937273 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6605. Min Range: -4.6605
Max Act: 4.5042. Min Act: -0.1700
Data Index: 4589665 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6605. Min Range: -4.6605
Max Act: 4.5042. Min Act: -0.1700
Data Index: 8783740 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6605. Min Range: -4.6605
Max Act: 4.4730. Min Act: -0.1700
Data Index: 8103756 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6605. Min Range: -4.6605
Max Act: 4.4730. Min Act: -0.1700
Data Index: 8663820 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6605. Min Range: -4.6605
Max Act: 4.4730. Min Act: -0.1700
Data Index: 3200335 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6605. Min Range: -4.6605
Max Act: 4.4417. Min Act: -0.1700
Data Index: 2335454 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6605. Min Range: -4.6605
Max Act: 4.4417. Min Act: -0.1700
Data Index: 6844522 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6605. Min Range: -4.6605
Max Act: 4.4417. Min Act: -0.1700
Data Index: 6604950 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6605. Min Range: -4.6605
Max Act: 4.4417. Min Act: -0.1700
Data Index: 5848746 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6605. Min Range: -4.6605
Max Act: 4.4417. Min Act: -0.1700
Data Index: 3582268 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6605. Min Range: -4.6605
Max Act: 4.4417. Min Act: -0.1700
Data Index: 3491868 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6605. Min Range: -4.6605
Max Act: 4.4105. Min Act: -0.1700
Data Index: 4172522 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6605. Min Range: -4.6605
Max Act: 4.4105. Min Act: -0.1700
Data Index: 3175470 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6605. Min Range: -4.6605
Max Act: 4.4105. Min Act: -0.1700
Data Index: 826163 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6605. Min Range: -4.6605
Max Act: 4.4105. Min Act: -0.1700
Data Index: 5677294 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #19