Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3304 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0923. Min Range: -7.0923
Max Act: 7.0923. Min Act: -0.1700
Data Index: 1647939 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0923. Min Range: -7.0923
Max Act: 6.8423. Min Act: -0.1700
Data Index: 5184606 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0923. Min Range: -7.0923
Max Act: 6.7798. Min Act: -0.1700
Data Index: 5644637 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0923. Min Range: -7.0923
Max Act: 6.6548. Min Act: -0.1700
Data Index: 2384804 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0923. Min Range: -7.0923
Max Act: 6.5923. Min Act: -0.1700
Data Index: 8267974 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0923. Min Range: -7.0923
Max Act: 6.5923. Min Act: -0.1700
Data Index: 5641299 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0923. Min Range: -7.0923
Max Act: 6.5611. Min Act: -0.1700
Data Index: 1421337 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0923. Min Range: -7.0923
Max Act: 6.5923. Min Act: -0.1700
Data Index: 3704568 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0923. Min Range: -7.0923
Max Act: 6.5611. Min Act: -0.1700
Data Index: 2053286 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0923. Min Range: -7.0923
Max Act: 6.4673. Min Act: -0.1700
Data Index: 5249450 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0923. Min Range: -7.0923
Max Act: 6.4673. Min Act: -0.1700
Data Index: 62340 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0923. Min Range: -7.0923
Max Act: 6.4361. Min Act: -0.1700
Data Index: 2383606 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0923. Min Range: -7.0923
Max Act: 6.4361. Min Act: -0.1700
Data Index: 3674314 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0923. Min Range: -7.0923
Max Act: 6.4048. Min Act: -0.1700
Data Index: 4659756 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0923. Min Range: -7.0923
Max Act: 6.4048. Min Act: -0.1700
Data Index: 2007416 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0923. Min Range: -7.0923
Max Act: 6.4048. Min Act: -0.1700
Data Index: 4393576 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0923. Min Range: -7.0923
Max Act: 6.4361. Min Act: -0.1700
Data Index: 5479369 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0923. Min Range: -7.0923
Max Act: 6.3736. Min Act: -0.1700
Data Index: 1884702 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0923. Min Range: -7.0923
Max Act: 6.3736. Min Act: -0.1700
Data Index: 5560647 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0923. Min Range: -7.0923
Max Act: 6.3423. Min Act: -0.1700
Data Index: 544727 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #19