Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6353 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5274. Min Range: -5.5274
Max Act: 5.5274. Min Act: -0.1700
Data Index: 5496914 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5274. Min Range: -5.5274
Max Act: 5.4649. Min Act: -0.1700
Data Index: 2493115 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5274. Min Range: -5.5274
Max Act: 5.4024. Min Act: -0.1700
Data Index: 2861684 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5274. Min Range: -5.5274
Max Act: 5.3087. Min Act: -0.1700
Data Index: 2242693 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5274. Min Range: -5.5274
Max Act: 5.2774. Min Act: -0.1700
Data Index: 2651441 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5274. Min Range: -5.5274
Max Act: 5.2774. Min Act: -0.1700
Data Index: 3042440 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5274. Min Range: -5.5274
Max Act: 5.2462. Min Act: -0.1700
Data Index: 1738994 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5274. Min Range: -5.5274
Max Act: 5.2462. Min Act: -0.1700
Data Index: 1739205 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5274. Min Range: -5.5274
Max Act: 5.2462. Min Act: -0.1700
Data Index: 2947575 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5274. Min Range: -5.5274
Max Act: 5.1837. Min Act: -0.1700
Data Index: 561712 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5274. Min Range: -5.5274
Max Act: 5.1837. Min Act: -0.1700
Data Index: 2754217 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5274. Min Range: -5.5274
Max Act: 5.1524. Min Act: -0.1700
Data Index: 717730 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5274. Min Range: -5.5274
Max Act: 5.1524. Min Act: -0.1700
Data Index: 783271 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5274. Min Range: -5.5274
Max Act: 5.0899. Min Act: -0.1700
Data Index: 1096671 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5274. Min Range: -5.5274
Max Act: 5.1524. Min Act: -0.1700
Data Index: 1377270 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5274. Min Range: -5.5274
Max Act: 5.1212. Min Act: -0.1700
Data Index: 6441260 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5274. Min Range: -5.5274
Max Act: 5.1212. Min Act: -0.1700
Data Index: 7255173 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5274. Min Range: -5.5274
Max Act: 5.1212. Min Act: -0.1700
Data Index: 2368216 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5274. Min Range: -5.5274
Max Act: 5.0899. Min Act: -0.1700
Data Index: 1610889 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5274. Min Range: -5.5274
Max Act: 5.0899. Min Act: -0.1700
Data Index: 99330 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #19