Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2633 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.4761. Min Range: -6.4761
Max Act: 6.4761. Min Act: -0.1700
Data Index: 3912730 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4761. Min Range: -6.4761
Max Act: 6.0698. Min Act: -0.1700
Data Index: 4886736 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4761. Min Range: -6.4761
Max Act: 6.0698. Min Act: -0.1700
Data Index: 2508761 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4761. Min Range: -6.4761
Max Act: 5.9136. Min Act: -0.1700
Data Index: 766289 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4761. Min Range: -6.4761
Max Act: 5.8823. Min Act: -0.1700
Data Index: 6820641 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4761. Min Range: -6.4761
Max Act: 5.8198. Min Act: -0.1700
Data Index: 1330353 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4761. Min Range: -6.4761
Max Act: 5.7573. Min Act: -0.1700
Data Index: 1409968 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4761. Min Range: -6.4761
Max Act: 5.7261. Min Act: -0.1700
Data Index: 743474 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4761. Min Range: -6.4761
Max Act: 5.7261. Min Act: -0.1700
Data Index: 8496896 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4761. Min Range: -6.4761
Max Act: 5.6636. Min Act: -0.1700
Data Index: 763130 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4761. Min Range: -6.4761
Max Act: 5.6948. Min Act: -0.1700
Data Index: 4550195 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4761. Min Range: -6.4761
Max Act: 5.7261. Min Act: -0.1700
Data Index: 5916933 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4761. Min Range: -6.4761
Max Act: 5.6948. Min Act: -0.1700
Data Index: 1602468 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4761. Min Range: -6.4761
Max Act: 5.6323. Min Act: -0.1700
Data Index: 1436496 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4761. Min Range: -6.4761
Max Act: 5.6636. Min Act: -0.1700
Data Index: 590085 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4761. Min Range: -6.4761
Max Act: 5.6636. Min Act: -0.1700
Data Index: 2666645 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4761. Min Range: -6.4761
Max Act: 5.6636. Min Act: -0.1700
Data Index: 5517582 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4761. Min Range: -6.4761
Max Act: 5.6636. Min Act: -0.1700
Data Index: 5762858 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4761. Min Range: -6.4761
Max Act: 5.6323. Min Act: -0.1700
Data Index: 5256086 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4761. Min Range: -6.4761
Max Act: 5.6323. Min Act: -0.1700
Data Index: 3000836 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #19