Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4661 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.4823. Min Range: -4.4823
Max Act: 4.4823. Min Act: -0.1700
Data Index: 3625295 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4823. Min Range: -4.4823
Max Act: 4.2948. Min Act: -0.1700
Data Index: 1760114 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4823. Min Range: -4.4823
Max Act: 4.2635. Min Act: -0.1700
Data Index: 1587170 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4823. Min Range: -4.4823
Max Act: 4.2323. Min Act: -0.1700
Data Index: 5955018 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4823. Min Range: -4.4823
Max Act: 4.2323. Min Act: -0.1700
Data Index: 925551 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4823. Min Range: -4.4823
Max Act: 4.1698. Min Act: -0.1700
Data Index: 3587507 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4823. Min Range: -4.4823
Max Act: 4.2010. Min Act: -0.1700
Data Index: 6237603 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4823. Min Range: -4.4823
Max Act: 4.1698. Min Act: -0.1700
Data Index: 7968775 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4823. Min Range: -4.4823
Max Act: 4.1073. Min Act: -0.1700
Data Index: 7144090 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4823. Min Range: -4.4823
Max Act: 4.1385. Min Act: -0.1700
Data Index: 1027281 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4823. Min Range: -4.4823
Max Act: 4.1385. Min Act: -0.1700
Data Index: 4058164 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4823. Min Range: -4.4823
Max Act: 4.1385. Min Act: -0.1700
Data Index: 4095997 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4823. Min Range: -4.4823
Max Act: 4.1698. Min Act: -0.1700
Data Index: 6176464 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4823. Min Range: -4.4823
Max Act: 4.1073. Min Act: -0.1700
Data Index: 5433049 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4823. Min Range: -4.4823
Max Act: 4.1073. Min Act: -0.1700
Data Index: 3274123 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4823. Min Range: -4.4823
Max Act: 4.1073. Min Act: -0.1700
Data Index: 5470488 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4823. Min Range: -4.4823
Max Act: 4.1073. Min Act: -0.1700
Data Index: 1584857 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4823. Min Range: -4.4823
Max Act: 4.1073. Min Act: -0.1700
Data Index: 2614674 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4823. Min Range: -4.4823
Max Act: 4.1073. Min Act: -0.1700
Data Index: 837269 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4823. Min Range: -4.4823
Max Act: 4.1073. Min Act: -0.1700
Data Index: 2545680 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #19