Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2659 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.2779. Min Range: -1.2779
Max Act: 1.2779. Min Act: -0.1700
Data Index: 1077306 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.2779. Min Range: -1.2779
Max Act: 1.2603. Min Act: -0.1700
Data Index: 2237936 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.2779. Min Range: -1.2779
Max Act: 1.2250. Min Act: -0.1699
Data Index: 2131406 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.2779. Min Range: -1.2779
Max Act: 1.2426. Min Act: -0.1700
Data Index: 6331291 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.2779. Min Range: -1.2779
Max Act: 1.2250. Min Act: -0.1700
Data Index: 2305489 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.2779. Min Range: -1.2779
Max Act: 1.2250. Min Act: -0.1700
Data Index: 632109 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.2779. Min Range: -1.2779
Max Act: 1.2250. Min Act: -0.1699
Data Index: 1322477 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.2779. Min Range: -1.2779
Max Act: 1.2074. Min Act: -0.1700
Data Index: 4774620 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.2779. Min Range: -1.2779
Max Act: 1.1898. Min Act: -0.1687
Data Index: 1780399 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.2779. Min Range: -1.2779
Max Act: 1.1722. Min Act: -0.1700
Data Index: 10315 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.2779. Min Range: -1.2779
Max Act: 1.1722. Min Act: -0.1700
Data Index: 2288851 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.2779. Min Range: -1.2779
Max Act: 1.1722. Min Act: -0.1696
Data Index: 2895420 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.2779. Min Range: -1.2779
Max Act: 1.1722. Min Act: -0.1700
Data Index: 2124084 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.2779. Min Range: -1.2779
Max Act: 1.1546. Min Act: -0.1700
Data Index: 1322717 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.2779. Min Range: -1.2779
Max Act: 1.1370. Min Act: -0.1700
Data Index: 5409688 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.2779. Min Range: -1.2779
Max Act: 1.1546. Min Act: -0.1700
Data Index: 8470088 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.2779. Min Range: -1.2779
Max Act: 1.1722. Min Act: -0.1690
Data Index: 2843505 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.2779. Min Range: -1.2779
Max Act: 1.1370. Min Act: -0.1682
Data Index: 3227023 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.2779. Min Range: -1.2779
Max Act: 1.1370. Min Act: -0.1699
Data Index: 7561650 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.2779. Min Range: -1.2779
Max Act: 1.1370. Min Act: -0.1699
Data Index: 4011884 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #19