Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3600 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4831. Min Range: -8.4831
Max Act: 8.4831. Min Act: -0.1700
Data Index: 1856007 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4831. Min Range: -8.4831
Max Act: 8.3581. Min Act: -0.1700
Data Index: 1999442 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4831. Min Range: -8.4831
Max Act: 8.3581. Min Act: -0.1700
Data Index: 860016 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4831. Min Range: -8.4831
Max Act: 8.1394. Min Act: -0.1700
Data Index: 5090951 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4831. Min Range: -8.4831
Max Act: 7.9831. Min Act: -0.1700
Data Index: 2940882 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4831. Min Range: -8.4831
Max Act: 7.9831. Min Act: -0.1700
Data Index: 1034052 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4831. Min Range: -8.4831
Max Act: 8.0144. Min Act: -0.1700
Data Index: 482614 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4831. Min Range: -8.4831
Max Act: 7.9831. Min Act: -0.1700
Data Index: 2307160 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4831. Min Range: -8.4831
Max Act: 7.9519. Min Act: -0.1700
Data Index: 1975008 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4831. Min Range: -8.4831
Max Act: 7.9519. Min Act: -0.1700
Data Index: 6089474 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4831. Min Range: -8.4831
Max Act: 8.0144. Min Act: -0.1700
Data Index: 7773019 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4831. Min Range: -8.4831
Max Act: 7.8581. Min Act: -0.1700
Data Index: 5937532 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4831. Min Range: -8.4831
Max Act: 7.8581. Min Act: -0.1700
Data Index: 7328888 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4831. Min Range: -8.4831
Max Act: 7.8894. Min Act: -0.1700
Data Index: 8287595 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4831. Min Range: -8.4831
Max Act: 7.7956. Min Act: -0.1700
Data Index: 3750055 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4831. Min Range: -8.4831
Max Act: 7.8269. Min Act: -0.1700
Data Index: 3944451 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4831. Min Range: -8.4831
Max Act: 7.8269. Min Act: -0.1700
Data Index: 4532729 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4831. Min Range: -8.4831
Max Act: 7.7956. Min Act: -0.1700
Data Index: 7726431 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4831. Min Range: -8.4831
Max Act: 7.7956. Min Act: -0.1700
Data Index: 7578615 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4831. Min Range: -8.4831
Max Act: 7.7331. Min Act: -0.1700
Data Index: 3971887 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #19