Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4786 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8440. Min Range: -5.8440
Max Act: 5.8440. Min Act: -0.1700
Data Index: 5801831 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8440. Min Range: -5.8440
Max Act: 5.5940. Min Act: -0.1700
Data Index: 6033915 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8440. Min Range: -5.8440
Max Act: 5.5940. Min Act: -0.1697
Data Index: 8636129 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8440. Min Range: -5.8440
Max Act: 5.3752. Min Act: -0.1700
Data Index: 1794081 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8440. Min Range: -5.8440
Max Act: 5.3440. Min Act: -0.1700
Data Index: 4008571 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8440. Min Range: -5.8440
Max Act: 5.3440. Min Act: -0.1700
Data Index: 3537671 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8440. Min Range: -5.8440
Max Act: 5.2815. Min Act: -0.1700
Data Index: 2801930 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8440. Min Range: -5.8440
Max Act: 5.2815. Min Act: -0.1700
Data Index: 6127181 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8440. Min Range: -5.8440
Max Act: 5.2815. Min Act: -0.1700
Data Index: 6698238 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8440. Min Range: -5.8440
Max Act: 5.2815. Min Act: -0.1700
Data Index: 4461790 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8440. Min Range: -5.8440
Max Act: 5.2190. Min Act: -0.1700
Data Index: 4765677 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8440. Min Range: -5.8440
Max Act: 5.2190. Min Act: -0.1700
Data Index: 5530645 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8440. Min Range: -5.8440
Max Act: 5.1877. Min Act: -0.1700
Data Index: 3809814 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8440. Min Range: -5.8440
Max Act: 5.1565. Min Act: -0.1700
Data Index: 6871182 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8440. Min Range: -5.8440
Max Act: 5.1565. Min Act: -0.1700
Data Index: 3111014 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8440. Min Range: -5.8440
Max Act: 5.1252. Min Act: -0.1700
Data Index: 524368 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8440. Min Range: -5.8440
Max Act: 5.1252. Min Act: -0.1700
Data Index: 2895001 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8440. Min Range: -5.8440
Max Act: 5.1252. Min Act: -0.1700
Data Index: 1124827 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8440. Min Range: -5.8440
Max Act: 5.1565. Min Act: -0.1700
Data Index: 4330322 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8440. Min Range: -5.8440
Max Act: 5.0940. Min Act: -0.1700
Data Index: 5520310 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #19