Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5226 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2551. Min Range: -7.2551
Max Act: 7.2551. Min Act: -0.1700
Data Index: 1549242 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2551. Min Range: -7.2551
Max Act: 7.1926. Min Act: -0.1700
Data Index: 1858261 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2551. Min Range: -7.2551
Max Act: 7.2551. Min Act: -0.1700
Data Index: 3410623 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2551. Min Range: -7.2551
Max Act: 7.0676. Min Act: -0.1700
Data Index: 7049393 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2551. Min Range: -7.2551
Max Act: 7.0364. Min Act: -0.1700
Data Index: 6108570 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2551. Min Range: -7.2551
Max Act: 6.9739. Min Act: -0.1700
Data Index: 1889592 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2551. Min Range: -7.2551
Max Act: 6.9114. Min Act: -0.1700
Data Index: 5683970 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2551. Min Range: -7.2551
Max Act: 6.8801. Min Act: -0.1700
Data Index: 6989241 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2551. Min Range: -7.2551
Max Act: 6.8489. Min Act: -0.1700
Data Index: 1760319 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2551. Min Range: -7.2551
Max Act: 6.8801. Min Act: -0.1700
Data Index: 7534186 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2551. Min Range: -7.2551
Max Act: 6.8489. Min Act: -0.1700
Data Index: 8618447 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2551. Min Range: -7.2551
Max Act: 6.8801. Min Act: -0.1697
Data Index: 4843256 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2551. Min Range: -7.2551
Max Act: 6.7551. Min Act: -0.1700
Data Index: 3152082 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2551. Min Range: -7.2551
Max Act: 6.7864. Min Act: -0.1700
Data Index: 5663200 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2551. Min Range: -7.2551
Max Act: 6.7551. Min Act: -0.1700
Data Index: 4950496 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2551. Min Range: -7.2551
Max Act: 6.7551. Min Act: -0.1700
Data Index: 6069434 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2551. Min Range: -7.2551
Max Act: 6.7239. Min Act: -0.1699
Data Index: 7629924 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2551. Min Range: -7.2551
Max Act: 6.7551. Min Act: -0.1700
Data Index: 3486709 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2551. Min Range: -7.2551
Max Act: 6.6926. Min Act: -0.1700
Data Index: 8234807 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2551. Min Range: -7.2551
Max Act: 6.6926. Min Act: -0.1700
Data Index: 4051918 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #19