Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1999 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5071. Min Range: -8.5071
Max Act: 8.5071. Min Act: -0.1700
Data Index: 4956047 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5071. Min Range: -8.5071
Max Act: 8.3196. Min Act: -0.1700
Data Index: 4134944 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5071. Min Range: -8.5071
Max Act: 8.1321. Min Act: -0.1700
Data Index: 8202861 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5071. Min Range: -8.5071
Max Act: 8.0696. Min Act: -0.1700
Data Index: 5561689 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5071. Min Range: -8.5071
Max Act: 8.0071. Min Act: -0.1700
Data Index: 2225083 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5071. Min Range: -8.5071
Max Act: 8.0071. Min Act: -0.1700
Data Index: 782008 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5071. Min Range: -8.5071
Max Act: 7.9446. Min Act: -0.1700
Data Index: 7472056 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5071. Min Range: -8.5071
Max Act: 7.9446. Min Act: -0.1700
Data Index: 4408504 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5071. Min Range: -8.5071
Max Act: 7.9446. Min Act: -0.1700
Data Index: 7190614 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5071. Min Range: -8.5071
Max Act: 7.8196. Min Act: -0.1700
Data Index: 1147046 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5071. Min Range: -8.5071
Max Act: 7.8196. Min Act: -0.1700
Data Index: 1398038 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5071. Min Range: -8.5071
Max Act: 7.8821. Min Act: -0.1700
Data Index: 6461865 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5071. Min Range: -8.5071
Max Act: 7.6946. Min Act: -0.1700
Data Index: 1060927 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5071. Min Range: -8.5071
Max Act: 7.7571. Min Act: -0.1700
Data Index: 1616878 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5071. Min Range: -8.5071
Max Act: 7.7571. Min Act: -0.1700
Data Index: 7148094 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5071. Min Range: -8.5071
Max Act: 7.7571. Min Act: -0.1700
Data Index: 5448656 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5071. Min Range: -8.5071
Max Act: 7.6946. Min Act: -0.1700
Data Index: 6604080 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5071. Min Range: -8.5071
Max Act: 7.6946. Min Act: -0.1700
Data Index: 7352569 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5071. Min Range: -8.5071
Max Act: 7.6946. Min Act: -0.1700
Data Index: 3574683 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5071. Min Range: -8.5071
Max Act: 7.6321. Min Act: -0.1700
Data Index: 4713608 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #19