Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5897 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4987. Min Range: -6.4987
Max Act: 6.4987. Min Act: -0.1700
Data Index: 6494797 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4987. Min Range: -6.4987
Max Act: 6.3425. Min Act: -0.1700
Data Index: 753690 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4987. Min Range: -6.4987
Max Act: 6.3425. Min Act: -0.1700
Data Index: 4443332 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4987. Min Range: -6.4987
Max Act: 6.2800. Min Act: -0.1700
Data Index: 3345313 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4987. Min Range: -6.4987
Max Act: 6.1862. Min Act: -0.1700
Data Index: 4524390 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4987. Min Range: -6.4987
Max Act: 6.0925. Min Act: -0.1700
Data Index: 7707511 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4987. Min Range: -6.4987
Max Act: 6.0925. Min Act: -0.1700
Data Index: 753435 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4987. Min Range: -6.4987
Max Act: 6.0612. Min Act: -0.1700
Data Index: 3633908 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4987. Min Range: -6.4987
Max Act: 6.0300. Min Act: -0.1700
Data Index: 106478 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4987. Min Range: -6.4987
Max Act: 6.0300. Min Act: -0.1700
Data Index: 7685362 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4987. Min Range: -6.4987
Max Act: 6.0300. Min Act: -0.1700
Data Index: 7643539 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4987. Min Range: -6.4987
Max Act: 5.9987. Min Act: -0.1700
Data Index: 5232332 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4987. Min Range: -6.4987
Max Act: 6.0300. Min Act: -0.1700
Data Index: 5079493 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4987. Min Range: -6.4987
Max Act: 5.9675. Min Act: -0.1700
Data Index: 7776926 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4987. Min Range: -6.4987
Max Act: 5.9675. Min Act: -0.1700
Data Index: 2305354 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4987. Min Range: -6.4987
Max Act: 5.9362. Min Act: -0.1700
Data Index: 4166605 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4987. Min Range: -6.4987
Max Act: 5.9050. Min Act: -0.1700
Data Index: 2229112 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4987. Min Range: -6.4987
Max Act: 5.9050. Min Act: -0.1700
Data Index: 8134399 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4987. Min Range: -6.4987
Max Act: 5.9050. Min Act: -0.1700
Data Index: 2634917 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4987. Min Range: -6.4987
Max Act: 5.9050. Min Act: -0.1700
Data Index: 872606 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #19