Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5435 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.4793. Min Range: -2.4793
Max Act: 2.4793. Min Act: -0.1700
Data Index: 7602241 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4793. Min Range: -2.4793
Max Act: 2.3489. Min Act: -0.1700
Data Index: 2510205 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4793. Min Range: -2.4793
Max Act: 2.2832. Min Act: -0.1700
Data Index: 6493923 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4793. Min Range: -2.4793
Max Act: 2.2667. Min Act: -0.1700
Data Index: 7344631 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4793. Min Range: -2.4793
Max Act: 2.2336. Min Act: -0.1700
Data Index: 1071981 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4793. Min Range: -2.4793
Max Act: 2.2171. Min Act: -0.1700
Data Index: 3707264 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4793. Min Range: -2.4793
Max Act: 2.2005. Min Act: -0.1700
Data Index: 4205543 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4793. Min Range: -2.4793
Max Act: 2.1672. Min Act: -0.1700
Data Index: 2416120 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4793. Min Range: -2.4793
Max Act: 2.1506. Min Act: -0.1700
Data Index: 4226302 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4793. Min Range: -2.4793
Max Act: 2.1506. Min Act: -0.1700
Data Index: 6493924 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4793. Min Range: -2.4793
Max Act: 2.1339. Min Act: -0.1700
Data Index: 3916003 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4793. Min Range: -2.4793
Max Act: 2.1339. Min Act: -0.1700
Data Index: 845765 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4793. Min Range: -2.4793
Max Act: 2.1339. Min Act: -0.1700
Data Index: 7923480 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4793. Min Range: -2.4793
Max Act: 2.1172. Min Act: -0.1700
Data Index: 425640 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4793. Min Range: -2.4793
Max Act: 2.1005. Min Act: -0.1700
Data Index: 2697188 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4793. Min Range: -2.4793
Max Act: 2.0837. Min Act: -0.1700
Data Index: 2203787 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4793. Min Range: -2.4793
Max Act: 2.0837. Min Act: -0.1700
Data Index: 2613710 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4793. Min Range: -2.4793
Max Act: 2.1005. Min Act: -0.1700
Data Index: 2222478 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4793. Min Range: -2.4793
Max Act: 2.1005. Min Act: -0.1700
Data Index: 2637446 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4793. Min Range: -2.4793
Max Act: 2.1005. Min Act: -0.1700
Data Index: 6772949 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #19