Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2821 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9187. Min Range: -5.9187
Max Act: 5.9187. Min Act: -0.1700
Data Index: 912019 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9187. Min Range: -5.9187
Max Act: 5.6374. Min Act: -0.1700
Data Index: 7358922 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9187. Min Range: -5.9187
Max Act: 5.6062. Min Act: -0.1700
Data Index: 6070351 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9187. Min Range: -5.9187
Max Act: 5.6062. Min Act: -0.1700
Data Index: 7174719 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9187. Min Range: -5.9187
Max Act: 5.5749. Min Act: -0.1700
Data Index: 316749 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9187. Min Range: -5.9187
Max Act: 5.5437. Min Act: -0.1700
Data Index: 7077493 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9187. Min Range: -5.9187
Max Act: 5.4812. Min Act: -0.1700
Data Index: 6086194 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9187. Min Range: -5.9187
Max Act: 5.4812. Min Act: -0.1700
Data Index: 6587472 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9187. Min Range: -5.9187
Max Act: 5.4812. Min Act: -0.1700
Data Index: 116088 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9187. Min Range: -5.9187
Max Act: 5.4499. Min Act: -0.1700
Data Index: 1580016 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9187. Min Range: -5.9187
Max Act: 5.4499. Min Act: -0.1700
Data Index: 2590382 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9187. Min Range: -5.9187
Max Act: 5.4187. Min Act: -0.1700
Data Index: 577704 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9187. Min Range: -5.9187
Max Act: 5.4187. Min Act: -0.1700
Data Index: 1595112 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9187. Min Range: -5.9187
Max Act: 5.3562. Min Act: -0.1700
Data Index: 7778966 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9187. Min Range: -5.9187
Max Act: 5.3874. Min Act: -0.1700
Data Index: 6152973 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9187. Min Range: -5.9187
Max Act: 5.3874. Min Act: -0.1700
Data Index: 8301549 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9187. Min Range: -5.9187
Max Act: 5.3874. Min Act: -0.1700
Data Index: 1084180 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9187. Min Range: -5.9187
Max Act: 5.3562. Min Act: -0.1700
Data Index: 5402007 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9187. Min Range: -5.9187
Max Act: 5.3562. Min Act: -0.1699
Data Index: 6222792 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9187. Min Range: -5.9187
Max Act: 5.3562. Min Act: -0.1700
Data Index: 3199777 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #19