Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1928 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7525. Min Range: -5.7525
Max Act: 5.7525. Min Act: -0.1700
Data Index: 6351542 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7525. Min Range: -5.7525
Max Act: 5.5650. Min Act: -0.1700
Data Index: 3095163 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7525. Min Range: -5.7525
Max Act: 5.4087. Min Act: -0.1700
Data Index: 6428665 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7525. Min Range: -5.7525
Max Act: 5.3150. Min Act: -0.1700
Data Index: 348250 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7525. Min Range: -5.7525
Max Act: 5.2212. Min Act: -0.1700
Data Index: 5912254 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7525. Min Range: -5.7525
Max Act: 5.1900. Min Act: -0.1700
Data Index: 4574715 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7525. Min Range: -5.7525
Max Act: 5.1587. Min Act: -0.1700
Data Index: 7420354 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7525. Min Range: -5.7525
Max Act: 5.1587. Min Act: -0.1700
Data Index: 4841854 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7525. Min Range: -5.7525
Max Act: 5.1275. Min Act: -0.1700
Data Index: 348248 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7525. Min Range: -5.7525
Max Act: 5.1275. Min Act: -0.1700
Data Index: 4604688 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7525. Min Range: -5.7525
Max Act: 5.0962. Min Act: -0.1700
Data Index: 3678080 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7525. Min Range: -5.7525
Max Act: 5.0962. Min Act: -0.1700
Data Index: 2601301 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7525. Min Range: -5.7525
Max Act: 5.0650. Min Act: -0.1700
Data Index: 4014028 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7525. Min Range: -5.7525
Max Act: 5.0650. Min Act: -0.1700
Data Index: 7966986 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7525. Min Range: -5.7525
Max Act: 5.0650. Min Act: -0.1700
Data Index: 5887363 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7525. Min Range: -5.7525
Max Act: 5.0650. Min Act: -0.1700
Data Index: 1397861 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7525. Min Range: -5.7525
Max Act: 5.0337. Min Act: -0.1700
Data Index: 2513228 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7525. Min Range: -5.7525
Max Act: 5.0650. Min Act: -0.1700
Data Index: 5494335 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7525. Min Range: -5.7525
Max Act: 5.0337. Min Act: -0.1700
Data Index: 5031505 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7525. Min Range: -5.7525
Max Act: 5.0025. Min Act: -0.1700
Data Index: 1397851 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #19