Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1715 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.7749. Min Range: -5.7749
Max Act: 5.7749. Min Act: -0.1700
Data Index: 3574913 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7749. Min Range: -5.7749
Max Act: 5.7437. Min Act: -0.1700
Data Index: 1073055 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7749. Min Range: -5.7749
Max Act: 5.6812. Min Act: -0.1700
Data Index: 6625264 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7749. Min Range: -5.7749
Max Act: 5.5562. Min Act: -0.1700
Data Index: 4073180 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7749. Min Range: -5.7749
Max Act: 5.5562. Min Act: -0.1700
Data Index: 8020919 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7749. Min Range: -5.7749
Max Act: 5.5562. Min Act: -0.1700
Data Index: 2988586 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7749. Min Range: -5.7749
Max Act: 5.5249. Min Act: -0.1700
Data Index: 2389783 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7749. Min Range: -5.7749
Max Act: 5.5249. Min Act: -0.1700
Data Index: 4443952 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7749. Min Range: -5.7749
Max Act: 5.4937. Min Act: -0.1700
Data Index: 7435270 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7749. Min Range: -5.7749
Max Act: 5.4624. Min Act: -0.1700
Data Index: 275742 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7749. Min Range: -5.7749
Max Act: 5.4312. Min Act: -0.1700
Data Index: 8652093 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7749. Min Range: -5.7749
Max Act: 5.4312. Min Act: -0.1700
Data Index: 3852854 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7749. Min Range: -5.7749
Max Act: 5.3999. Min Act: -0.1700
Data Index: 7597378 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7749. Min Range: -5.7749
Max Act: 5.3999. Min Act: -0.1700
Data Index: 2066138 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7749. Min Range: -5.7749
Max Act: 5.3999. Min Act: -0.1700
Data Index: 3192919 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7749. Min Range: -5.7749
Max Act: 5.3999. Min Act: -0.1700
Data Index: 6112586 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7749. Min Range: -5.7749
Max Act: 5.4312. Min Act: -0.1700
Data Index: 2775797 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7749. Min Range: -5.7749
Max Act: 5.3999. Min Act: -0.1700
Data Index: 7822933 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7749. Min Range: -5.7749
Max Act: 5.3687. Min Act: -0.1700
Data Index: 7893916 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7749. Min Range: -5.7749
Max Act: 5.3687. Min Act: -0.1700
Data Index: 7931683 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #19