Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4582 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.8846. Min Range: -2.8846
Max Act: 2.8846. Min Act: -0.1700
Data Index: 1726922 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8846. Min Range: -2.8846
Max Act: 2.8687. Min Act: -0.1700
Data Index: 3841743 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8846. Min Range: -2.8846
Max Act: 2.8687. Min Act: -0.1700
Data Index: 3849400 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8846. Min Range: -2.8846
Max Act: 2.8211. Min Act: -0.1700
Data Index: 728951 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8846. Min Range: -2.8846
Max Act: 2.8211. Min Act: -0.1700
Data Index: 1638258 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8846. Min Range: -2.8846
Max Act: 2.7733. Min Act: -0.1700
Data Index: 6917617 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8846. Min Range: -2.8846
Max Act: 2.7254. Min Act: -0.1700
Data Index: 2374041 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8846. Min Range: -2.8846
Max Act: 2.7254. Min Act: -0.1700
Data Index: 1881455 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8846. Min Range: -2.8846
Max Act: 2.7094. Min Act: -0.1700
Data Index: 7595945 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8846. Min Range: -2.8846
Max Act: 2.6934. Min Act: -0.1700
Data Index: 3497663 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8846. Min Range: -2.8846
Max Act: 2.6934. Min Act: -0.1700
Data Index: 5734195 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8846. Min Range: -2.8846
Max Act: 2.6613. Min Act: -0.1700
Data Index: 6062245 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8846. Min Range: -2.8846
Max Act: 2.6453. Min Act: -0.1700
Data Index: 2028438 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8846. Min Range: -2.8846
Max Act: 2.6453. Min Act: -0.1700
Data Index: 2849592 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8846. Min Range: -2.8846
Max Act: 2.6292. Min Act: -0.1700
Data Index: 3297305 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8846. Min Range: -2.8846
Max Act: 2.6453. Min Act: -0.1700
Data Index: 7555407 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8846. Min Range: -2.8846
Max Act: 2.6453. Min Act: -0.1700
Data Index: 5247731 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8846. Min Range: -2.8846
Max Act: 2.6292. Min Act: -0.1700
Data Index: 3497664 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8846. Min Range: -2.8846
Max Act: 2.6292. Min Act: -0.1700
Data Index: 5432742 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8846. Min Range: -2.8846
Max Act: 2.6613. Min Act: -0.1700
Data Index: 7701862 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #19