Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4859 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.9058. Min Range: -2.9058
Max Act: 2.9058. Min Act: -0.1700
Data Index: 825955 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9058. Min Range: -2.9058
Max Act: 2.8105. Min Act: -0.1700
Data Index: 2891814 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9058. Min Range: -2.9058
Max Act: 2.7945. Min Act: -0.1700
Data Index: 8311383 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9058. Min Range: -2.9058
Max Act: 2.7945. Min Act: -0.1700
Data Index: 3773 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9058. Min Range: -2.9058
Max Act: 2.7945. Min Act: -0.1700
Data Index: 3699002 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9058. Min Range: -2.9058
Max Act: 2.7786. Min Act: -0.1700
Data Index: 6796042 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9058. Min Range: -2.9058
Max Act: 2.7786. Min Act: -0.1700
Data Index: 7687148 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9058. Min Range: -2.9058
Max Act: 2.7786. Min Act: -0.1700
Data Index: 3225545 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9058. Min Range: -2.9058
Max Act: 2.7467. Min Act: -0.1700
Data Index: 4953379 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9058. Min Range: -2.9058
Max Act: 2.7307. Min Act: -0.1700
Data Index: 5388434 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9058. Min Range: -2.9058
Max Act: 2.7307. Min Act: -0.1700
Data Index: 6463548 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9058. Min Range: -2.9058
Max Act: 2.7307. Min Act: -0.1700
Data Index: 7537357 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9058. Min Range: -2.9058
Max Act: 2.7307. Min Act: -0.1700
Data Index: 8594153 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9058. Min Range: -2.9058
Max Act: 2.7307. Min Act: -0.1700
Data Index: 1093266 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9058. Min Range: -2.9058
Max Act: 2.6988. Min Act: -0.1700
Data Index: 6549559 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9058. Min Range: -2.9058
Max Act: 2.7148. Min Act: -0.1700
Data Index: 3889420 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9058. Min Range: -2.9058
Max Act: 2.7148. Min Act: -0.1700
Data Index: 1269882 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9058. Min Range: -2.9058
Max Act: 2.7148. Min Act: -0.1700
Data Index: 3904175 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9058. Min Range: -2.9058
Max Act: 2.7148. Min Act: -0.1700
Data Index: 2942450 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9058. Min Range: -2.9058
Max Act: 2.7148. Min Act: -0.1700
Data Index: 799667 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #19