Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3583 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0590. Min Range: -6.0590
Max Act: 6.0590. Min Act: -0.1700
Data Index: 1837153 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0590. Min Range: -6.0590
Max Act: 5.9965. Min Act: -0.1700
Data Index: 6859407 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0590. Min Range: -6.0590
Max Act: 5.9965. Min Act: -0.1700
Data Index: 5767435 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0590. Min Range: -6.0590
Max Act: 5.9965. Min Act: -0.1700
Data Index: 8043133 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0590. Min Range: -6.0590
Max Act: 5.9965. Min Act: -0.1700
Data Index: 6206705 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0590. Min Range: -6.0590
Max Act: 5.9028. Min Act: -0.1700
Data Index: 1017711 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0590. Min Range: -6.0590
Max Act: 5.9340. Min Act: -0.1700
Data Index: 20064 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0590. Min Range: -6.0590
Max Act: 5.9028. Min Act: -0.1700
Data Index: 4456294 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0590. Min Range: -6.0590
Max Act: 5.9028. Min Act: -0.1700
Data Index: 4946130 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0590. Min Range: -6.0590
Max Act: 5.9028. Min Act: -0.1700
Data Index: 2309594 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0590. Min Range: -6.0590
Max Act: 5.8403. Min Act: -0.1700
Data Index: 4334572 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0590. Min Range: -6.0590
Max Act: 5.8403. Min Act: -0.1700
Data Index: 2014413 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0590. Min Range: -6.0590
Max Act: 5.8403. Min Act: -0.1700
Data Index: 7669261 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0590. Min Range: -6.0590
Max Act: 5.8403. Min Act: -0.1700
Data Index: 7831361 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0590. Min Range: -6.0590
Max Act: 5.8403. Min Act: -0.1700
Data Index: 4591714 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0590. Min Range: -6.0590
Max Act: 5.8090. Min Act: -0.1700
Data Index: 218378 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0590. Min Range: -6.0590
Max Act: 5.8090. Min Act: -0.1700
Data Index: 4334957 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0590. Min Range: -6.0590
Max Act: 5.7778. Min Act: -0.1700
Data Index: 7117590 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0590. Min Range: -6.0590
Max Act: 5.7778. Min Act: -0.1700
Data Index: 7715244 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0590. Min Range: -6.0590
Max Act: 5.8090. Min Act: -0.1700
Data Index: 6319570 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #19