Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2647 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1003. Min Range: -5.1003
Max Act: 5.1003. Min Act: -0.1700
Data Index: 1651893 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1003. Min Range: -5.1003
Max Act: 5.0690. Min Act: -0.1700
Data Index: 4211553 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1003. Min Range: -5.1003
Max Act: 4.9440. Min Act: -0.1700
Data Index: 1218039 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1003. Min Range: -5.1003
Max Act: 4.8815. Min Act: -0.1700
Data Index: 5809124 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1003. Min Range: -5.1003
Max Act: 4.8503. Min Act: -0.1700
Data Index: 6107751 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1003. Min Range: -5.1003
Max Act: 4.8190. Min Act: -0.1700
Data Index: 3735324 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1003. Min Range: -5.1003
Max Act: 4.8190. Min Act: -0.1700
Data Index: 2076593 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1003. Min Range: -5.1003
Max Act: 4.7878. Min Act: -0.1700
Data Index: 8356131 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1003. Min Range: -5.1003
Max Act: 4.7878. Min Act: -0.1700
Data Index: 5104288 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1003. Min Range: -5.1003
Max Act: 4.7253. Min Act: -0.1700
Data Index: 7424026 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1003. Min Range: -5.1003
Max Act: 4.6940. Min Act: -0.1700
Data Index: 7228767 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1003. Min Range: -5.1003
Max Act: 4.6940. Min Act: -0.1700
Data Index: 1437809 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1003. Min Range: -5.1003
Max Act: 4.6003. Min Act: -0.1700
Data Index: 860680 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1003. Min Range: -5.1003
Max Act: 4.6003. Min Act: -0.1700
Data Index: 3877744 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1003. Min Range: -5.1003
Max Act: 4.6003. Min Act: -0.1700
Data Index: 7981755 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1003. Min Range: -5.1003
Max Act: 4.5690. Min Act: -0.1700
Data Index: 3993749 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1003. Min Range: -5.1003
Max Act: 4.6003. Min Act: -0.1700
Data Index: 8460513 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1003. Min Range: -5.1003
Max Act: 4.5690. Min Act: -0.1700
Data Index: 7733454 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1003. Min Range: -5.1003
Max Act: 4.5690. Min Act: -0.1700
Data Index: 2262308 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1003. Min Range: -5.1003
Max Act: 4.5690. Min Act: -0.1700
Data Index: 4813462 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #19