Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1804 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0994. Min Range: -7.0994
Max Act: 7.0994. Min Act: -0.1700
Data Index: 2725672 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0994. Min Range: -7.0994
Max Act: 6.6931. Min Act: -0.1700
Data Index: 6153142 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0994. Min Range: -7.0994
Max Act: 6.5056. Min Act: -0.1700
Data Index: 6554751 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0994. Min Range: -7.0994
Max Act: 6.5056. Min Act: -0.1700
Data Index: 5816967 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0994. Min Range: -7.0994
Max Act: 6.4431. Min Act: -0.1700
Data Index: 1065183 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0994. Min Range: -7.0994
Max Act: 6.3806. Min Act: -0.1700
Data Index: 2771385 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0994. Min Range: -7.0994
Max Act: 6.3806. Min Act: -0.1700
Data Index: 6391374 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0994. Min Range: -7.0994
Max Act: 6.3181. Min Act: -0.1700
Data Index: 4814594 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0994. Min Range: -7.0994
Max Act: 6.2869. Min Act: -0.1700
Data Index: 6150432 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0994. Min Range: -7.0994
Max Act: 6.2869. Min Act: -0.1700
Data Index: 8584 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0994. Min Range: -7.0994
Max Act: 6.2869. Min Act: -0.1700
Data Index: 7727180 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0994. Min Range: -7.0994
Max Act: 6.2869. Min Act: -0.1700
Data Index: 3326314 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0994. Min Range: -7.0994
Max Act: 6.2869. Min Act: -0.1700
Data Index: 252066 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0994. Min Range: -7.0994
Max Act: 6.2869. Min Act: -0.1700
Data Index: 3960513 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0994. Min Range: -7.0994
Max Act: 6.2244. Min Act: -0.1700
Data Index: 504463 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0994. Min Range: -7.0994
Max Act: 6.2244. Min Act: -0.1700
Data Index: 8267648 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0994. Min Range: -7.0994
Max Act: 6.1931. Min Act: -0.1700
Data Index: 4524564 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0994. Min Range: -7.0994
Max Act: 6.1931. Min Act: -0.1700
Data Index: 5612837 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0994. Min Range: -7.0994
Max Act: 6.1619. Min Act: -0.1700
Data Index: 4884726 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0994. Min Range: -7.0994
Max Act: 6.1619. Min Act: -0.1700
Data Index: 5292954 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #19