Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4544 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8884. Min Range: -3.8884
Max Act: 3.8884. Min Act: -0.1700
Data Index: 7916800 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8884. Min Range: -3.8884
Max Act: 3.8258. Min Act: -0.1700
Data Index: 8186051 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8884. Min Range: -3.8884
Max Act: 3.7320. Min Act: -0.1700
Data Index: 8199046 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8884. Min Range: -3.8884
Max Act: 3.6694. Min Act: -0.1700
Data Index: 4159442 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8884. Min Range: -3.8884
Max Act: 3.6694. Min Act: -0.1700
Data Index: 2916904 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8884. Min Range: -3.8884
Max Act: 3.6694. Min Act: -0.1700
Data Index: 6360008 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8884. Min Range: -3.8884
Max Act: 3.6694. Min Act: -0.1700
Data Index: 6040203 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8884. Min Range: -3.8884
Max Act: 3.6694. Min Act: -0.1686
Data Index: 8110267 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8884. Min Range: -3.8884
Max Act: 3.6694. Min Act: -0.1699
Data Index: 7677920 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8884. Min Range: -3.8884
Max Act: 3.6694. Min Act: -0.1700
Data Index: 8242801 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8884. Min Range: -3.8884
Max Act: 3.6381. Min Act: -0.1700
Data Index: 1383686 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8884. Min Range: -3.8884
Max Act: 3.6381. Min Act: -0.1700
Data Index: 8160247 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8884. Min Range: -3.8884
Max Act: 3.6381. Min Act: -0.1700
Data Index: 463402 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8884. Min Range: -3.8884
Max Act: 3.6381. Min Act: -0.1698
Data Index: 434886 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8884. Min Range: -3.8884
Max Act: 3.6381. Min Act: -0.1700
Data Index: 356971 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8884. Min Range: -3.8884
Max Act: 3.6068. Min Act: -0.1698
Data Index: 5958496 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8884. Min Range: -3.8884
Max Act: 3.6068. Min Act: -0.1700
Data Index: 7369686 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8884. Min Range: -3.8884
Max Act: 3.6068. Min Act: -0.1700
Data Index: 2043296 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8884. Min Range: -3.8884
Max Act: 3.6068. Min Act: -0.1700
Data Index: 7134804 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8884. Min Range: -3.8884
Max Act: 3.6068. Min Act: -0.1700
Data Index: 2947016 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #19