Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2946 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6370. Min Range: -6.6370
Max Act: 6.6370. Min Act: -0.1700
Data Index: 8694664 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6370. Min Range: -6.6370
Max Act: 6.1995. Min Act: -0.1700
Data Index: 1774227 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6370. Min Range: -6.6370
Max Act: 6.1370. Min Act: -0.1700
Data Index: 6427748 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6370. Min Range: -6.6370
Max Act: 6.1057. Min Act: -0.1700
Data Index: 1296679 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6370. Min Range: -6.6370
Max Act: 6.0432. Min Act: -0.1700
Data Index: 8338233 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6370. Min Range: -6.6370
Max Act: 5.9807. Min Act: -0.1700
Data Index: 918416 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6370. Min Range: -6.6370
Max Act: 5.9495. Min Act: -0.1700
Data Index: 5862518 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6370. Min Range: -6.6370
Max Act: 5.9495. Min Act: -0.1700
Data Index: 8274772 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6370. Min Range: -6.6370
Max Act: 5.9495. Min Act: -0.1700
Data Index: 6352018 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6370. Min Range: -6.6370
Max Act: 5.9182. Min Act: -0.1700
Data Index: 6660540 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6370. Min Range: -6.6370
Max Act: 5.8870. Min Act: -0.1700
Data Index: 4887597 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6370. Min Range: -6.6370
Max Act: 5.8557. Min Act: -0.1700
Data Index: 4496888 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6370. Min Range: -6.6370
Max Act: 5.8870. Min Act: -0.1700
Data Index: 8644836 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6370. Min Range: -6.6370
Max Act: 5.8245. Min Act: -0.1700
Data Index: 7229338 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6370. Min Range: -6.6370
Max Act: 5.7932. Min Act: -0.1700
Data Index: 3066180 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6370. Min Range: -6.6370
Max Act: 5.7932. Min Act: -0.1700
Data Index: 1961145 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6370. Min Range: -6.6370
Max Act: 5.7932. Min Act: -0.1700
Data Index: 5933031 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6370. Min Range: -6.6370
Max Act: 5.7620. Min Act: -0.1700
Data Index: 6205448 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6370. Min Range: -6.6370
Max Act: 5.7620. Min Act: -0.1700
Data Index: 8082108 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6370. Min Range: -6.6370
Max Act: 5.7620. Min Act: -0.1700
Data Index: 2824031 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #19