Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 596 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2032. Min Range: -6.2032
Max Act: 6.2032. Min Act: -0.1700
Data Index: 3836474 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2032. Min Range: -6.2032
Max Act: 6.1719. Min Act: -0.1700
Data Index: 5686855 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2032. Min Range: -6.2032
Max Act: 6.0782. Min Act: -0.1700
Data Index: 6215309 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2032. Min Range: -6.2032
Max Act: 6.0157. Min Act: -0.1700
Data Index: 6380336 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2032. Min Range: -6.2032
Max Act: 5.9532. Min Act: -0.1700
Data Index: 6424799 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2032. Min Range: -6.2032
Max Act: 5.9532. Min Act: -0.1700
Data Index: 4806796 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2032. Min Range: -6.2032
Max Act: 5.9532. Min Act: -0.1700
Data Index: 1825568 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2032. Min Range: -6.2032
Max Act: 5.9219. Min Act: -0.1700
Data Index: 6052861 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2032. Min Range: -6.2032
Max Act: 5.9219. Min Act: -0.1700
Data Index: 3997497 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2032. Min Range: -6.2032
Max Act: 5.9219. Min Act: -0.1700
Data Index: 5140644 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2032. Min Range: -6.2032
Max Act: 5.8594. Min Act: -0.1700
Data Index: 1813885 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2032. Min Range: -6.2032
Max Act: 5.8594. Min Act: -0.1700
Data Index: 5200668 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2032. Min Range: -6.2032
Max Act: 5.8282. Min Act: -0.1700
Data Index: 7582094 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2032. Min Range: -6.2032
Max Act: 5.8282. Min Act: -0.1700
Data Index: 2464095 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2032. Min Range: -6.2032
Max Act: 5.8594. Min Act: -0.1700
Data Index: 6613332 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2032. Min Range: -6.2032
Max Act: 5.8282. Min Act: -0.1700
Data Index: 5899804 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2032. Min Range: -6.2032
Max Act: 5.8282. Min Act: -0.1700
Data Index: 4630572 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2032. Min Range: -6.2032
Max Act: 5.7969. Min Act: -0.1700
Data Index: 4386849 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2032. Min Range: -6.2032
Max Act: 5.7969. Min Act: -0.1700
Data Index: 6602087 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2032. Min Range: -6.2032
Max Act: 5.8282. Min Act: -0.1700
Data Index: 7850950 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #19