Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4043 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.6591. Min Range: -3.6591
Max Act: 3.6591. Min Act: -0.1700
Data Index: 4600227 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6591. Min Range: -3.6591
Max Act: 3.6278. Min Act: -0.1700
Data Index: 4715025 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6591. Min Range: -3.6591
Max Act: 3.6278. Min Act: -0.1700
Data Index: 13998 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6591. Min Range: -3.6591
Max Act: 3.5808. Min Act: -0.1700
Data Index: 8211548 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6591. Min Range: -3.6591
Max Act: 3.5025. Min Act: -0.1700
Data Index: 1865481 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6591. Min Range: -3.6591
Max Act: 3.4869. Min Act: -0.1700
Data Index: 8133495 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6591. Min Range: -3.6591
Max Act: 3.4712. Min Act: -0.1700
Data Index: 657963 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6591. Min Range: -3.6591
Max Act: 3.4556. Min Act: -0.1700
Data Index: 8552801 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6591. Min Range: -3.6591
Max Act: 3.4399. Min Act: -0.1700
Data Index: 3744490 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6591. Min Range: -3.6591
Max Act: 3.4085. Min Act: -0.1700
Data Index: 2746199 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6591. Min Range: -3.6591
Max Act: 3.4242. Min Act: -0.1700
Data Index: 1104953 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6591. Min Range: -3.6591
Max Act: 3.4085. Min Act: -0.1700
Data Index: 1455523 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6591. Min Range: -3.6591
Max Act: 3.4085. Min Act: -0.1700
Data Index: 3638322 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6591. Min Range: -3.6591
Max Act: 3.4085. Min Act: -0.1700
Data Index: 3793489 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6591. Min Range: -3.6591
Max Act: 3.3772. Min Act: -0.1700
Data Index: 2264951 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6591. Min Range: -3.6591
Max Act: 3.3772. Min Act: -0.1700
Data Index: 4742641 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6591. Min Range: -3.6591
Max Act: 3.3929. Min Act: -0.1700
Data Index: 5705666 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6591. Min Range: -3.6591
Max Act: 3.3615. Min Act: -0.1700
Data Index: 4742662 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6591. Min Range: -3.6591
Max Act: 3.3772. Min Act: -0.1700
Data Index: 389584 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6591. Min Range: -3.6591
Max Act: 3.3458. Min Act: -0.1700
Data Index: 44187 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #19