Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2923 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6779. Min Range: -8.6779
Max Act: 8.6779. Min Act: -0.1700
Data Index: 1226277 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6779. Min Range: -8.6779
Max Act: 8.4904. Min Act: -0.1700
Data Index: 715897 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6779. Min Range: -8.6779
Max Act: 8.3654. Min Act: -0.1700
Data Index: 4024155 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6779. Min Range: -8.6779
Max Act: 8.3654. Min Act: -0.1700
Data Index: 6273849 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6779. Min Range: -8.6779
Max Act: 8.3654. Min Act: -0.1700
Data Index: 212402 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6779. Min Range: -8.6779
Max Act: 8.3029. Min Act: -0.1700
Data Index: 6382856 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6779. Min Range: -8.6779
Max Act: 8.3029. Min Act: -0.1700
Data Index: 6404103 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6779. Min Range: -8.6779
Max Act: 8.2404. Min Act: -0.1700
Data Index: 5074134 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6779. Min Range: -8.6779
Max Act: 8.2404. Min Act: -0.1700
Data Index: 6809814 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6779. Min Range: -8.6779
Max Act: 8.2404. Min Act: -0.1700
Data Index: 4152637 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6779. Min Range: -8.6779
Max Act: 8.1779. Min Act: -0.1700
Data Index: 6461757 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6779. Min Range: -8.6779
Max Act: 8.1466. Min Act: -0.1700
Data Index: 6036884 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6779. Min Range: -8.6779
Max Act: 8.1466. Min Act: -0.1700
Data Index: 8044727 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6779. Min Range: -8.6779
Max Act: 8.1466. Min Act: -0.1700
Data Index: 1554357 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6779. Min Range: -8.6779
Max Act: 8.1154. Min Act: -0.1700
Data Index: 5602022 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6779. Min Range: -8.6779
Max Act: 8.1154. Min Act: -0.1700
Data Index: 5117857 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6779. Min Range: -8.6779
Max Act: 8.1154. Min Act: -0.1700
Data Index: 2593979 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6779. Min Range: -8.6779
Max Act: 8.0841. Min Act: -0.1700
Data Index: 4709968 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6779. Min Range: -8.6779
Max Act: 8.0841. Min Act: -0.1700
Data Index: 5544766 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6779. Min Range: -8.6779
Max Act: 8.0841. Min Act: -0.1700
Data Index: 4738828 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #19