Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5152 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0350. Min Range: -7.0350
Max Act: 7.0350. Min Act: -0.1700
Data Index: 4830214 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0350. Min Range: -7.0350
Max Act: 6.7850. Min Act: -0.1700
Data Index: 748177 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0350. Min Range: -7.0350
Max Act: 6.7225. Min Act: -0.1700
Data Index: 2588806 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0350. Min Range: -7.0350
Max Act: 6.7225. Min Act: -0.1700
Data Index: 767644 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0350. Min Range: -7.0350
Max Act: 6.6600. Min Act: -0.1700
Data Index: 8282640 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0350. Min Range: -7.0350
Max Act: 6.6287. Min Act: -0.1700
Data Index: 3456938 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0350. Min Range: -7.0350
Max Act: 6.5350. Min Act: -0.1700
Data Index: 767645 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0350. Min Range: -7.0350
Max Act: 6.5037. Min Act: -0.1700
Data Index: 1609300 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0350. Min Range: -7.0350
Max Act: 6.5350. Min Act: -0.1700
Data Index: 1629410 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0350. Min Range: -7.0350
Max Act: 6.5037. Min Act: -0.1700
Data Index: 6820236 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0350. Min Range: -7.0350
Max Act: 6.5037. Min Act: -0.1700
Data Index: 1131904 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0350. Min Range: -7.0350
Max Act: 6.4100. Min Act: -0.1700
Data Index: 2159950 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0350. Min Range: -7.0350
Max Act: 6.4100. Min Act: -0.1700
Data Index: 7089363 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0350. Min Range: -7.0350
Max Act: 6.4100. Min Act: -0.1700
Data Index: 818966 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0350. Min Range: -7.0350
Max Act: 6.4100. Min Act: -0.1700
Data Index: 2259003 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0350. Min Range: -7.0350
Max Act: 6.4412. Min Act: -0.1700
Data Index: 973300 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0350. Min Range: -7.0350
Max Act: 6.3787. Min Act: -0.1700
Data Index: 1976840 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0350. Min Range: -7.0350
Max Act: 6.3787. Min Act: -0.1700
Data Index: 5785559 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0350. Min Range: -7.0350
Max Act: 6.3787. Min Act: -0.1700
Data Index: 5140882 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0350. Min Range: -7.0350
Max Act: 6.3787. Min Act: -0.1700
Data Index: 6443809 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #19