Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4917 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9025. Min Range: -5.9025
Max Act: 5.9025. Min Act: -0.1700
Data Index: 8731349 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9025. Min Range: -5.9025
Max Act: 5.7775. Min Act: -0.1700
Data Index: 1795789 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9025. Min Range: -5.9025
Max Act: 5.7462. Min Act: -0.1700
Data Index: 6753968 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9025. Min Range: -5.9025
Max Act: 5.7150. Min Act: -0.1700
Data Index: 4749991 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9025. Min Range: -5.9025
Max Act: 5.6837. Min Act: -0.1700
Data Index: 4690414 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9025. Min Range: -5.9025
Max Act: 5.6525. Min Act: -0.1700
Data Index: 4594725 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9025. Min Range: -5.9025
Max Act: 5.6525. Min Act: -0.1700
Data Index: 5111248 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9025. Min Range: -5.9025
Max Act: 5.6525. Min Act: -0.1700
Data Index: 5491349 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9025. Min Range: -5.9025
Max Act: 5.6525. Min Act: -0.1700
Data Index: 3241273 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9025. Min Range: -5.9025
Max Act: 5.6525. Min Act: -0.1700
Data Index: 5494145 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9025. Min Range: -5.9025
Max Act: 5.6525. Min Act: -0.1700
Data Index: 1147861 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9025. Min Range: -5.9025
Max Act: 5.6212. Min Act: -0.1700
Data Index: 7975710 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9025. Min Range: -5.9025
Max Act: 5.5587. Min Act: -0.1700
Data Index: 3515745 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9025. Min Range: -5.9025
Max Act: 5.5900. Min Act: -0.1700
Data Index: 4747942 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9025. Min Range: -5.9025
Max Act: 5.5900. Min Act: -0.1700
Data Index: 4357819 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9025. Min Range: -5.9025
Max Act: 5.5587. Min Act: -0.1700
Data Index: 85139 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9025. Min Range: -5.9025
Max Act: 5.5587. Min Act: -0.1700
Data Index: 7258811 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9025. Min Range: -5.9025
Max Act: 5.5275. Min Act: -0.1700
Data Index: 3569068 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9025. Min Range: -5.9025
Max Act: 5.5587. Min Act: -0.1700
Data Index: 5652966 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9025. Min Range: -5.9025
Max Act: 5.5275. Min Act: -0.1700
Data Index: 6095793 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #19