Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3829 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9061. Min Range: -5.9061
Max Act: 5.9061. Min Act: -0.1700
Data Index: 6166200 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9061. Min Range: -5.9061
Max Act: 5.8124. Min Act: -0.1700
Data Index: 5695528 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9061. Min Range: -5.9061
Max Act: 5.8124. Min Act: -0.1700
Data Index: 6166181 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9061. Min Range: -5.9061
Max Act: 5.7499. Min Act: -0.1700
Data Index: 3718177 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9061. Min Range: -5.9061
Max Act: 5.7186. Min Act: -0.1700
Data Index: 6166192 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9061. Min Range: -5.9061
Max Act: 5.7186. Min Act: -0.1700
Data Index: 5484550 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9061. Min Range: -5.9061
Max Act: 5.7499. Min Act: -0.1700
Data Index: 6166199 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9061. Min Range: -5.9061
Max Act: 5.7186. Min Act: -0.1700
Data Index: 6166191 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9061. Min Range: -5.9061
Max Act: 5.6874. Min Act: -0.1700
Data Index: 8686674 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9061. Min Range: -5.9061
Max Act: 5.6874. Min Act: -0.1700
Data Index: 6166201 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9061. Min Range: -5.9061
Max Act: 5.6874. Min Act: -0.1700
Data Index: 1576203 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9061. Min Range: -5.9061
Max Act: 5.6874. Min Act: -0.1700
Data Index: 5355981 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9061. Min Range: -5.9061
Max Act: 5.6874. Min Act: -0.1700
Data Index: 255388 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9061. Min Range: -5.9061
Max Act: 5.6874. Min Act: -0.1700
Data Index: 6166193 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9061. Min Range: -5.9061
Max Act: 5.6561. Min Act: -0.1700
Data Index: 4103392 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9061. Min Range: -5.9061
Max Act: 5.6561. Min Act: -0.1700
Data Index: 6166185 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9061. Min Range: -5.9061
Max Act: 5.6874. Min Act: -0.1700
Data Index: 8686677 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9061. Min Range: -5.9061
Max Act: 5.6561. Min Act: -0.1700
Data Index: 907416 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9061. Min Range: -5.9061
Max Act: 5.6561. Min Act: -0.1700
Data Index: 6166195 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9061. Min Range: -5.9061
Max Act: 5.6249. Min Act: -0.1700
Data Index: 1576194 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #19