Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1625 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 13.1880. Min Range: -13.1880
Max Act: 13.1880. Min Act: -0.1700
Data Index: 5630403 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 13.1880. Min Range: -13.1880
Max Act: 13.1255. Min Act: -0.1700
Data Index: 158598 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 13.1880. Min Range: -13.1880
Max Act: 13.1255. Min Act: -0.1700
Data Index: 770236 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 13.1880. Min Range: -13.1880
Max Act: 13.0005. Min Act: -0.1700
Data Index: 5824755 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 13.1880. Min Range: -13.1880
Max Act: 13.0005. Min Act: -0.1700
Data Index: 5965996 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 13.1880. Min Range: -13.1880
Max Act: 12.9380. Min Act: -0.1700
Data Index: 5189197 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 13.1880. Min Range: -13.1880
Max Act: 12.8755. Min Act: -0.1700
Data Index: 656132 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 13.1880. Min Range: -13.1880
Max Act: 12.8130. Min Act: -0.1700
Data Index: 4534169 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 13.1880. Min Range: -13.1880
Max Act: 12.8130. Min Act: -0.1700
Data Index: 7503907 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 13.1880. Min Range: -13.1880
Max Act: 12.8130. Min Act: -0.1700
Data Index: 747891 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 13.1880. Min Range: -13.1880
Max Act: 12.8130. Min Act: -0.1700
Data Index: 1086906 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 13.1880. Min Range: -13.1880
Max Act: 12.8130. Min Act: -0.1700
Data Index: 8543028 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 13.1880. Min Range: -13.1880
Max Act: 12.8130. Min Act: -0.1700
Data Index: 855145 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 13.1880. Min Range: -13.1880
Max Act: 12.8130. Min Act: -0.1700
Data Index: 594023 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 13.1880. Min Range: -13.1880
Max Act: 12.8130. Min Act: -0.1700
Data Index: 2996667 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 13.1880. Min Range: -13.1880
Max Act: 12.8130. Min Act: -0.1700
Data Index: 1645261 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 13.1880. Min Range: -13.1880
Max Act: 12.8130. Min Act: -0.1700
Data Index: 7938946 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 13.1880. Min Range: -13.1880
Max Act: 12.8130. Min Act: -0.1700
Data Index: 6068718 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 13.1880. Min Range: -13.1880
Max Act: 12.7505. Min Act: -0.1700
Data Index: 671562 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 13.1880. Min Range: -13.1880
Max Act: 12.7505. Min Act: -0.1700
Data Index: 6533756 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #19