Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3902 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.2833. Min Range: -5.2833
Max Act: 5.2833. Min Act: -0.1700
Data Index: 291794 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2833. Min Range: -5.2833
Max Act: 5.2208. Min Act: -0.1700
Data Index: 5094584 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2833. Min Range: -5.2833
Max Act: 5.2208. Min Act: -0.1700
Data Index: 148539 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2833. Min Range: -5.2833
Max Act: 5.1583. Min Act: -0.1700
Data Index: 6414722 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2833. Min Range: -5.2833
Max Act: 5.1895. Min Act: -0.1700
Data Index: 1862156 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2833. Min Range: -5.2833
Max Act: 5.1270. Min Act: -0.1700
Data Index: 2805805 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2833. Min Range: -5.2833
Max Act: 5.0958. Min Act: -0.1700
Data Index: 115516 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2833. Min Range: -5.2833
Max Act: 5.0958. Min Act: -0.1700
Data Index: 3525793 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2833. Min Range: -5.2833
Max Act: 5.0958. Min Act: -0.1700
Data Index: 5445414 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2833. Min Range: -5.2833
Max Act: 5.0958. Min Act: -0.1700
Data Index: 4238737 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2833. Min Range: -5.2833
Max Act: 5.0645. Min Act: -0.1700
Data Index: 8729199 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2833. Min Range: -5.2833
Max Act: 5.0645. Min Act: -0.1700
Data Index: 4868665 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2833. Min Range: -5.2833
Max Act: 5.0645. Min Act: -0.1700
Data Index: 5011740 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2833. Min Range: -5.2833
Max Act: 5.0645. Min Act: -0.1700
Data Index: 5737488 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2833. Min Range: -5.2833
Max Act: 5.0645. Min Act: -0.1700
Data Index: 539031 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2833. Min Range: -5.2833
Max Act: 5.0645. Min Act: -0.1700
Data Index: 7664793 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2833. Min Range: -5.2833
Max Act: 5.0333. Min Act: -0.1700
Data Index: 660998 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2833. Min Range: -5.2833
Max Act: 5.0020. Min Act: -0.1700
Data Index: 6926943 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2833. Min Range: -5.2833
Max Act: 5.0333. Min Act: -0.1700
Data Index: 32895 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2833. Min Range: -5.2833
Max Act: 5.0333. Min Act: -0.1700
Data Index: 4211642 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #19