Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3487 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8439. Min Range: -5.8439
Max Act: 5.8439. Min Act: -0.1700
Data Index: 7723582 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8439. Min Range: -5.8439
Max Act: 5.8127. Min Act: -0.1700
Data Index: 5573239 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8439. Min Range: -5.8439
Max Act: 5.7814. Min Act: -0.1700
Data Index: 6834899 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8439. Min Range: -5.8439
Max Act: 5.7502. Min Act: -0.1700
Data Index: 2415489 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8439. Min Range: -5.8439
Max Act: 5.7189. Min Act: -0.1700
Data Index: 4403642 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8439. Min Range: -5.8439
Max Act: 5.7189. Min Act: -0.1700
Data Index: 3995234 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8439. Min Range: -5.8439
Max Act: 5.6877. Min Act: -0.1700
Data Index: 6095470 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8439. Min Range: -5.8439
Max Act: 5.6877. Min Act: -0.1700
Data Index: 6195328 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8439. Min Range: -5.8439
Max Act: 5.6564. Min Act: -0.1700
Data Index: 7567734 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8439. Min Range: -5.8439
Max Act: 5.6252. Min Act: -0.1700
Data Index: 4083574 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8439. Min Range: -5.8439
Max Act: 5.6564. Min Act: -0.1700
Data Index: 7523142 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8439. Min Range: -5.8439
Max Act: 5.5627. Min Act: -0.1700
Data Index: 1842832 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8439. Min Range: -5.8439
Max Act: 5.5939. Min Act: -0.1700
Data Index: 5980566 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8439. Min Range: -5.8439
Max Act: 5.5627. Min Act: -0.1700
Data Index: 6664978 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8439. Min Range: -5.8439
Max Act: 5.5314. Min Act: -0.1700
Data Index: 2367262 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8439. Min Range: -5.8439
Max Act: 5.5002. Min Act: -0.1700
Data Index: 2885876 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8439. Min Range: -5.8439
Max Act: 5.5002. Min Act: -0.1700
Data Index: 2367269 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8439. Min Range: -5.8439
Max Act: 5.4689. Min Act: -0.1700
Data Index: 4313324 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8439. Min Range: -5.8439
Max Act: 5.4689. Min Act: -0.1700
Data Index: 3441357 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8439. Min Range: -5.8439
Max Act: 5.4689. Min Act: -0.1700
Data Index: 2367267 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #19