Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3100 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5633. Min Range: -4.5633
Max Act: 4.5633. Min Act: -0.1700
Data Index: 2222567 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5633. Min Range: -4.5633
Max Act: 4.5320. Min Act: -0.1700
Data Index: 1078996 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5633. Min Range: -4.5633
Max Act: 4.5008. Min Act: -0.1700
Data Index: 3861860 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5633. Min Range: -4.5633
Max Act: 4.4695. Min Act: -0.1700
Data Index: 8106001 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5633. Min Range: -4.5633
Max Act: 4.4383. Min Act: -0.1700
Data Index: 4238779 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5633. Min Range: -4.5633
Max Act: 4.4695. Min Act: -0.1700
Data Index: 2697444 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5633. Min Range: -4.5633
Max Act: 4.4695. Min Act: -0.1700
Data Index: 732204 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5633. Min Range: -4.5633
Max Act: 4.4383. Min Act: -0.1700
Data Index: 1508270 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5633. Min Range: -4.5633
Max Act: 4.4383. Min Act: -0.1700
Data Index: 5055118 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5633. Min Range: -4.5633
Max Act: 4.4383. Min Act: -0.1700
Data Index: 503884 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5633. Min Range: -4.5633
Max Act: 4.4383. Min Act: -0.1700
Data Index: 7807173 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5633. Min Range: -4.5633
Max Act: 4.4695. Min Act: -0.1700
Data Index: 4515605 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5633. Min Range: -4.5633
Max Act: 4.4383. Min Act: -0.1700
Data Index: 1847775 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5633. Min Range: -4.5633
Max Act: 4.4070. Min Act: -0.1700
Data Index: 4158810 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5633. Min Range: -4.5633
Max Act: 4.4070. Min Act: -0.1700
Data Index: 5900109 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5633. Min Range: -4.5633
Max Act: 4.4070. Min Act: -0.1700
Data Index: 7222628 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5633. Min Range: -4.5633
Max Act: 4.4070. Min Act: -0.1700
Data Index: 1317770 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5633. Min Range: -4.5633
Max Act: 4.4070. Min Act: -0.1700
Data Index: 3445137 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5633. Min Range: -4.5633
Max Act: 4.4070. Min Act: -0.1700
Data Index: 3601304 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5633. Min Range: -4.5633
Max Act: 4.4070. Min Act: -0.1700
Data Index: 2948819 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #19