Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3516 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.4895. Min Range: -5.4895
Max Act: 5.4895. Min Act: -0.1700
Data Index: 3996071 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4895. Min Range: -5.4895
Max Act: 5.4582. Min Act: -0.1700
Data Index: 5004768 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4895. Min Range: -5.4895
Max Act: 5.3957. Min Act: -0.1700
Data Index: 3293212 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4895. Min Range: -5.4895
Max Act: 5.3645. Min Act: -0.1700
Data Index: 5209683 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4895. Min Range: -5.4895
Max Act: 5.3957. Min Act: -0.1700
Data Index: 7355404 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4895. Min Range: -5.4895
Max Act: 5.3645. Min Act: -0.1700
Data Index: 4741198 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4895. Min Range: -5.4895
Max Act: 5.3020. Min Act: -0.1700
Data Index: 3963164 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4895. Min Range: -5.4895
Max Act: 5.3020. Min Act: -0.1700
Data Index: 1013784 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4895. Min Range: -5.4895
Max Act: 5.2707. Min Act: -0.1700
Data Index: 6770428 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4895. Min Range: -5.4895
Max Act: 5.2395. Min Act: -0.1700
Data Index: 2643429 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4895. Min Range: -5.4895
Max Act: 5.2082. Min Act: -0.1700
Data Index: 7774544 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4895. Min Range: -5.4895
Max Act: 5.2082. Min Act: -0.1700
Data Index: 7634669 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4895. Min Range: -5.4895
Max Act: 5.1770. Min Act: -0.1700
Data Index: 7398458 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4895. Min Range: -5.4895
Max Act: 5.2082. Min Act: -0.1700
Data Index: 4416718 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4895. Min Range: -5.4895
Max Act: 5.1770. Min Act: -0.1700
Data Index: 5295131 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4895. Min Range: -5.4895
Max Act: 5.1770. Min Act: -0.1700
Data Index: 4173557 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4895. Min Range: -5.4895
Max Act: 5.1457. Min Act: -0.1700
Data Index: 4789517 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4895. Min Range: -5.4895
Max Act: 5.1145. Min Act: -0.1700
Data Index: 4260199 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4895. Min Range: -5.4895
Max Act: 5.1145. Min Act: -0.1700
Data Index: 5853722 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4895. Min Range: -5.4895
Max Act: 5.1457. Min Act: -0.1700
Data Index: 857325 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #19