Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1895 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0591. Min Range: -7.0591
Max Act: 7.0591. Min Act: -0.1700
Data Index: 5517363 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0591. Min Range: -7.0591
Max Act: 7.0591. Min Act: -0.1700
Data Index: 7921933 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0591. Min Range: -7.0591
Max Act: 7.0279. Min Act: -0.1700
Data Index: 3141741 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0591. Min Range: -7.0591
Max Act: 6.9654. Min Act: -0.1700
Data Index: 1131228 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0591. Min Range: -7.0591
Max Act: 6.8404. Min Act: -0.1700
Data Index: 8171175 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0591. Min Range: -7.0591
Max Act: 6.8716. Min Act: -0.1700
Data Index: 13952 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0591. Min Range: -7.0591
Max Act: 6.7466. Min Act: -0.1700
Data Index: 2118004 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0591. Min Range: -7.0591
Max Act: 6.7154. Min Act: -0.1700
Data Index: 7427764 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0591. Min Range: -7.0591
Max Act: 6.6216. Min Act: -0.1700
Data Index: 8671164 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0591. Min Range: -7.0591
Max Act: 6.5904. Min Act: -0.1700
Data Index: 7286969 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0591. Min Range: -7.0591
Max Act: 6.5904. Min Act: -0.1700
Data Index: 6713459 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0591. Min Range: -7.0591
Max Act: 6.5904. Min Act: -0.1700
Data Index: 6306663 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0591. Min Range: -7.0591
Max Act: 6.5904. Min Act: -0.1700
Data Index: 3984874 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0591. Min Range: -7.0591
Max Act: 6.5904. Min Act: -0.1700
Data Index: 1313719 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0591. Min Range: -7.0591
Max Act: 6.5591. Min Act: -0.1700
Data Index: 4425066 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0591. Min Range: -7.0591
Max Act: 6.5591. Min Act: -0.1700
Data Index: 2470189 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0591. Min Range: -7.0591
Max Act: 6.5591. Min Act: -0.1700
Data Index: 7172639 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0591. Min Range: -7.0591
Max Act: 6.5279. Min Act: -0.1700
Data Index: 1734805 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0591. Min Range: -7.0591
Max Act: 6.4966. Min Act: -0.1700
Data Index: 712046 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0591. Min Range: -7.0591
Max Act: 6.4966. Min Act: -0.1700
Data Index: 4367996 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #19