Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1483 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0773. Min Range: -4.0773
Max Act: 4.0773. Min Act: -0.1700
Data Index: 4834418 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0773. Min Range: -4.0773
Max Act: 4.0460. Min Act: -0.1700
Data Index: 8622265 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0773. Min Range: -4.0773
Max Act: 3.9523. Min Act: -0.1700
Data Index: 7255005 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0773. Min Range: -4.0773
Max Act: 3.9523. Min Act: -0.1700
Data Index: 968671 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0773. Min Range: -4.0773
Max Act: 3.8585. Min Act: -0.1700
Data Index: 7489096 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0773. Min Range: -4.0773
Max Act: 3.7959. Min Act: -0.1700
Data Index: 2629614 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0773. Min Range: -4.0773
Max Act: 3.7959. Min Act: -0.1700
Data Index: 7924546 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0773. Min Range: -4.0773
Max Act: 3.7959. Min Act: -0.1700
Data Index: 3627250 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0773. Min Range: -4.0773
Max Act: 3.7959. Min Act: -0.1700
Data Index: 4786757 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0773. Min Range: -4.0773
Max Act: 3.7959. Min Act: -0.1700
Data Index: 1788876 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0773. Min Range: -4.0773
Max Act: 3.7647. Min Act: -0.1700
Data Index: 7784581 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0773. Min Range: -4.0773
Max Act: 3.7647. Min Act: -0.1700
Data Index: 5377966 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0773. Min Range: -4.0773
Max Act: 3.7647. Min Act: -0.1700
Data Index: 8291452 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0773. Min Range: -4.0773
Max Act: 3.7334. Min Act: -0.1700
Data Index: 5147465 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0773. Min Range: -4.0773
Max Act: 3.7647. Min Act: -0.1700
Data Index: 4007494 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0773. Min Range: -4.0773
Max Act: 3.7334. Min Act: -0.1700
Data Index: 6219386 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0773. Min Range: -4.0773
Max Act: 3.7334. Min Act: -0.1700
Data Index: 4038866 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0773. Min Range: -4.0773
Max Act: 3.7021. Min Act: -0.1700
Data Index: 6625604 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0773. Min Range: -4.0773
Max Act: 3.7021. Min Act: -0.1700
Data Index: 5579105 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0773. Min Range: -4.0773
Max Act: 3.7334. Min Act: -0.1700
Data Index: 1531701 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #19