Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2600 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9067. Min Range: -7.9067
Max Act: 7.9067. Min Act: -0.1700
Data Index: 4173929 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9067. Min Range: -7.9067
Max Act: 7.2192. Min Act: -0.1700
Data Index: 3382695 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9067. Min Range: -7.9067
Max Act: 7.1567. Min Act: -0.1700
Data Index: 346746 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9067. Min Range: -7.9067
Max Act: 7.0942. Min Act: -0.1700
Data Index: 2173775 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9067. Min Range: -7.9067
Max Act: 7.0005. Min Act: -0.1700
Data Index: 5582877 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9067. Min Range: -7.9067
Max Act: 7.0005. Min Act: -0.1700
Data Index: 5806774 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9067. Min Range: -7.9067
Max Act: 7.0005. Min Act: -0.1700
Data Index: 7965431 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9067. Min Range: -7.9067
Max Act: 6.9380. Min Act: -0.1700
Data Index: 5629952 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9067. Min Range: -7.9067
Max Act: 6.9380. Min Act: -0.1700
Data Index: 2753922 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9067. Min Range: -7.9067
Max Act: 6.8755. Min Act: -0.1700
Data Index: 1127890 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9067. Min Range: -7.9067
Max Act: 6.8755. Min Act: -0.1700
Data Index: 3601793 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9067. Min Range: -7.9067
Max Act: 6.8755. Min Act: -0.1700
Data Index: 7567355 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9067. Min Range: -7.9067
Max Act: 6.8442. Min Act: -0.1700
Data Index: 3059179 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9067. Min Range: -7.9067
Max Act: 6.8130. Min Act: -0.1700
Data Index: 1362546 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9067. Min Range: -7.9067
Max Act: 6.8130. Min Act: -0.1700
Data Index: 7086911 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9067. Min Range: -7.9067
Max Act: 6.7817. Min Act: -0.1700
Data Index: 3293384 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9067. Min Range: -7.9067
Max Act: 6.7817. Min Act: -0.1700
Data Index: 958759 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9067. Min Range: -7.9067
Max Act: 6.7817. Min Act: -0.1700
Data Index: 5983934 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9067. Min Range: -7.9067
Max Act: 6.7505. Min Act: -0.1700
Data Index: 8696473 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9067. Min Range: -7.9067
Max Act: 6.7192. Min Act: -0.1700
Data Index: 5204804 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #19