Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 745 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.7621. Min Range: -6.7621
Max Act: 6.7621. Min Act: -0.1700
Data Index: 3281827 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7621. Min Range: -6.7621
Max Act: 6.7308. Min Act: -0.1700
Data Index: 7270386 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7621. Min Range: -6.7621
Max Act: 6.7308. Min Act: -0.1700
Data Index: 7387272 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7621. Min Range: -6.7621
Max Act: 6.6996. Min Act: -0.1700
Data Index: 7486170 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7621. Min Range: -6.7621
Max Act: 6.6683. Min Act: -0.1700
Data Index: 2143156 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7621. Min Range: -6.7621
Max Act: 6.6996. Min Act: -0.1700
Data Index: 240201 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7621. Min Range: -6.7621
Max Act: 6.6683. Min Act: -0.1700
Data Index: 6738829 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7621. Min Range: -6.7621
Max Act: 6.6371. Min Act: -0.1700
Data Index: 904161 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7621. Min Range: -6.7621
Max Act: 6.6683. Min Act: -0.1700
Data Index: 998281 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7621. Min Range: -6.7621
Max Act: 6.6371. Min Act: -0.1700
Data Index: 93382 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7621. Min Range: -6.7621
Max Act: 6.6058. Min Act: -0.1700
Data Index: 5801284 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7621. Min Range: -6.7621
Max Act: 6.6371. Min Act: -0.1700
Data Index: 1321682 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7621. Min Range: -6.7621
Max Act: 6.6371. Min Act: -0.1700
Data Index: 2894892 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7621. Min Range: -6.7621
Max Act: 6.6371. Min Act: -0.1700
Data Index: 2885715 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7621. Min Range: -6.7621
Max Act: 6.6058. Min Act: -0.1700
Data Index: 1081240 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7621. Min Range: -6.7621
Max Act: 6.6058. Min Act: -0.1700
Data Index: 2993907 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7621. Min Range: -6.7621
Max Act: 6.6058. Min Act: -0.1700
Data Index: 2756073 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7621. Min Range: -6.7621
Max Act: 6.6058. Min Act: -0.1700
Data Index: 3585500 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7621. Min Range: -6.7621
Max Act: 6.6058. Min Act: -0.1700
Data Index: 2191443 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7621. Min Range: -6.7621
Max Act: 6.6058. Min Act: -0.1700
Data Index: 1276893 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #19