Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2720 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.4729. Min Range: -8.4729
Max Act: 8.4729. Min Act: -0.1700
Data Index: 8535102 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4729. Min Range: -8.4729
Max Act: 8.4104. Min Act: -0.1700
Data Index: 1062462 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4729. Min Range: -8.4729
Max Act: 8.4104. Min Act: -0.1700
Data Index: 938580 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4729. Min Range: -8.4729
Max Act: 8.3479. Min Act: -0.1700
Data Index: 6585469 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4729. Min Range: -8.4729
Max Act: 8.3479. Min Act: -0.1700
Data Index: 988570 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4729. Min Range: -8.4729
Max Act: 8.2854. Min Act: -0.1700
Data Index: 7556023 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4729. Min Range: -8.4729
Max Act: 8.2854. Min Act: -0.1700
Data Index: 1933707 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4729. Min Range: -8.4729
Max Act: 8.2229. Min Act: -0.1700
Data Index: 938582 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4729. Min Range: -8.4729
Max Act: 8.2229. Min Act: -0.1700
Data Index: 995067 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4729. Min Range: -8.4729
Max Act: 8.1916. Min Act: -0.1700
Data Index: 2477782 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4729. Min Range: -8.4729
Max Act: 8.1916. Min Act: -0.1700
Data Index: 982751 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4729. Min Range: -8.4729
Max Act: 8.0979. Min Act: -0.1700
Data Index: 4525482 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4729. Min Range: -8.4729
Max Act: 8.0666. Min Act: -0.1700
Data Index: 3141908 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4729. Min Range: -8.4729
Max Act: 8.0041. Min Act: -0.1700
Data Index: 6025484 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4729. Min Range: -8.4729
Max Act: 7.9416. Min Act: -0.1700
Data Index: 982752 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4729. Min Range: -8.4729
Max Act: 7.9416. Min Act: -0.1700
Data Index: 4022045 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4729. Min Range: -8.4729
Max Act: 7.9729. Min Act: -0.1700
Data Index: 5609747 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4729. Min Range: -8.4729
Max Act: 7.9416. Min Act: -0.1700
Data Index: 6061424 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4729. Min Range: -8.4729
Max Act: 7.8479. Min Act: -0.1700
Data Index: 4190178 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4729. Min Range: -8.4729
Max Act: 7.8791. Min Act: -0.1700
Data Index: 3101064 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #19