Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4264 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6651. Min Range: -7.6651
Max Act: 7.6651. Min Act: -0.1700
Data Index: 1188072 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6651. Min Range: -7.6651
Max Act: 7.4776. Min Act: -0.1700
Data Index: 7243672 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6651. Min Range: -7.6651
Max Act: 7.3526. Min Act: -0.1700
Data Index: 7747296 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6651. Min Range: -7.6651
Max Act: 7.2276. Min Act: -0.1700
Data Index: 5067322 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6651. Min Range: -7.6651
Max Act: 7.2276. Min Act: -0.1700
Data Index: 5298378 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6651. Min Range: -7.6651
Max Act: 7.1651. Min Act: -0.1700
Data Index: 1775998 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6651. Min Range: -7.6651
Max Act: 7.1026. Min Act: -0.1700
Data Index: 3720579 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6651. Min Range: -7.6651
Max Act: 7.0401. Min Act: -0.1700
Data Index: 4314758 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6651. Min Range: -7.6651
Max Act: 7.0401. Min Act: -0.1700
Data Index: 6772625 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6651. Min Range: -7.6651
Max Act: 7.0401. Min Act: -0.1700
Data Index: 4248999 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6651. Min Range: -7.6651
Max Act: 7.0089. Min Act: -0.1700
Data Index: 3219174 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6651. Min Range: -7.6651
Max Act: 6.9151. Min Act: -0.1700
Data Index: 8069258 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6651. Min Range: -7.6651
Max Act: 6.9151. Min Act: -0.1700
Data Index: 4911808 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6651. Min Range: -7.6651
Max Act: 6.9464. Min Act: -0.1700
Data Index: 5473384 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6651. Min Range: -7.6651
Max Act: 6.9464. Min Act: -0.1700
Data Index: 403201 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6651. Min Range: -7.6651
Max Act: 6.9464. Min Act: -0.1700
Data Index: 6583708 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6651. Min Range: -7.6651
Max Act: 6.9464. Min Act: -0.1700
Data Index: 3199154 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6651. Min Range: -7.6651
Max Act: 6.8839. Min Act: -0.1700
Data Index: 2967898 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6651. Min Range: -7.6651
Max Act: 6.8839. Min Act: -0.1700
Data Index: 192341 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6651. Min Range: -7.6651
Max Act: 6.8839. Min Act: -0.1700
Data Index: 6506000 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #19