Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2187 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.3390. Min Range: -6.3390
Max Act: 6.3390. Min Act: -0.1700
Data Index: 6055805 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3390. Min Range: -6.3390
Max Act: 6.1515. Min Act: -0.1700
Data Index: 6808308 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3390. Min Range: -6.3390
Max Act: 5.9328. Min Act: -0.1700
Data Index: 2869022 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3390. Min Range: -6.3390
Max Act: 5.9015. Min Act: -0.1700
Data Index: 5375497 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3390. Min Range: -6.3390
Max Act: 5.9015. Min Act: -0.1700
Data Index: 6418788 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3390. Min Range: -6.3390
Max Act: 5.8390. Min Act: -0.1700
Data Index: 2869021 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3390. Min Range: -6.3390
Max Act: 5.8078. Min Act: -0.1700
Data Index: 1861904 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3390. Min Range: -6.3390
Max Act: 5.8078. Min Act: -0.1700
Data Index: 7815458 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3390. Min Range: -6.3390
Max Act: 5.8078. Min Act: -0.1700
Data Index: 3501861 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3390. Min Range: -6.3390
Max Act: 5.7140. Min Act: -0.1700
Data Index: 1277505 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3390. Min Range: -6.3390
Max Act: 5.7140. Min Act: -0.1700
Data Index: 5967588 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3390. Min Range: -6.3390
Max Act: 5.5890. Min Act: -0.1700
Data Index: 4041610 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3390. Min Range: -6.3390
Max Act: 5.5578. Min Act: -0.1700
Data Index: 2312138 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3390. Min Range: -6.3390
Max Act: 5.5578. Min Act: -0.1700
Data Index: 7721055 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3390. Min Range: -6.3390
Max Act: 5.5578. Min Act: -0.1700
Data Index: 775871 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3390. Min Range: -6.3390
Max Act: 5.5578. Min Act: -0.1700
Data Index: 2700335 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3390. Min Range: -6.3390
Max Act: 5.5578. Min Act: -0.1700
Data Index: 3841194 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3390. Min Range: -6.3390
Max Act: 5.4640. Min Act: -0.1700
Data Index: 3554124 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3390. Min Range: -6.3390
Max Act: 5.4015. Min Act: -0.1700
Data Index: 3316901 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3390. Min Range: -6.3390
Max Act: 5.4328. Min Act: -0.1700
Data Index: 1393260 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #19