Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3479 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7505. Min Range: -8.7505
Max Act: 8.7505. Min Act: -0.1700
Data Index: 3140975 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7505. Min Range: -8.7505
Max Act: 8.7505. Min Act: -0.1700
Data Index: 3664324 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7505. Min Range: -8.7505
Max Act: 8.5630. Min Act: -0.1700
Data Index: 2715646 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7505. Min Range: -8.7505
Max Act: 8.4380. Min Act: -0.1700
Data Index: 866393 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7505. Min Range: -8.7505
Max Act: 8.3130. Min Act: -0.1700
Data Index: 8815315 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7505. Min Range: -8.7505
Max Act: 8.1880. Min Act: -0.1700
Data Index: 1948400 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7505. Min Range: -8.7505
Max Act: 8.1880. Min Act: -0.1700
Data Index: 8391545 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7505. Min Range: -8.7505
Max Act: 8.1255. Min Act: -0.1700
Data Index: 4592960 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7505. Min Range: -8.7505
Max Act: 8.1255. Min Act: -0.1700
Data Index: 4849679 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7505. Min Range: -8.7505
Max Act: 8.0630. Min Act: -0.1700
Data Index: 5994926 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7505. Min Range: -8.7505
Max Act: 8.0630. Min Act: -0.1700
Data Index: 6355734 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7505. Min Range: -8.7505
Max Act: 8.0005. Min Act: -0.1700
Data Index: 513300 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7505. Min Range: -8.7505
Max Act: 8.0005. Min Act: -0.1700
Data Index: 434347 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7505. Min Range: -8.7505
Max Act: 8.0005. Min Act: -0.1700
Data Index: 40785 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7505. Min Range: -8.7505
Max Act: 7.9380. Min Act: -0.1700
Data Index: 6975203 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7505. Min Range: -8.7505
Max Act: 7.8755. Min Act: -0.1700
Data Index: 1782465 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7505. Min Range: -8.7505
Max Act: 7.8130. Min Act: -0.1700
Data Index: 1764192 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7505. Min Range: -8.7505
Max Act: 7.8130. Min Act: -0.1700
Data Index: 3121385 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7505. Min Range: -8.7505
Max Act: 7.8130. Min Act: -0.1700
Data Index: 1731604 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7505. Min Range: -8.7505
Max Act: 7.8130. Min Act: -0.1700
Data Index: 8479800 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #19