Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4113 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0739. Min Range: -5.0739
Max Act: 5.0739. Min Act: -0.1700
Data Index: 1643966 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0739. Min Range: -5.0739
Max Act: 5.0114. Min Act: -0.1700
Data Index: 3488559 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0739. Min Range: -5.0739
Max Act: 5.0114. Min Act: -0.1700
Data Index: 65050 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0739. Min Range: -5.0739
Max Act: 4.9801. Min Act: -0.1700
Data Index: 5150756 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0739. Min Range: -5.0739
Max Act: 4.9801. Min Act: -0.1700
Data Index: 2500756 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0739. Min Range: -5.0739
Max Act: 4.8864. Min Act: -0.1700
Data Index: 6023322 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0739. Min Range: -5.0739
Max Act: 4.8864. Min Act: -0.1700
Data Index: 7372227 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0739. Min Range: -5.0739
Max Act: 4.9176. Min Act: -0.1700
Data Index: 4558193 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0739. Min Range: -5.0739
Max Act: 4.8551. Min Act: -0.1700
Data Index: 3634039 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0739. Min Range: -5.0739
Max Act: 4.8864. Min Act: -0.1700
Data Index: 1484532 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0739. Min Range: -5.0739
Max Act: 4.8239. Min Act: -0.1700
Data Index: 5051037 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0739. Min Range: -5.0739
Max Act: 4.7926. Min Act: -0.1700
Data Index: 7858828 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0739. Min Range: -5.0739
Max Act: 4.7926. Min Act: -0.1700
Data Index: 8462566 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0739. Min Range: -5.0739
Max Act: 4.7926. Min Act: -0.1700
Data Index: 1564606 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0739. Min Range: -5.0739
Max Act: 4.7926. Min Act: -0.1700
Data Index: 6029038 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0739. Min Range: -5.0739
Max Act: 4.7614. Min Act: -0.1700
Data Index: 7682528 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0739. Min Range: -5.0739
Max Act: 4.7614. Min Act: -0.1700
Data Index: 4751531 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0739. Min Range: -5.0739
Max Act: 4.7614. Min Act: -0.1700
Data Index: 5061816 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0739. Min Range: -5.0739
Max Act: 4.7301. Min Act: -0.1700
Data Index: 1797654 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0739. Min Range: -5.0739
Max Act: 4.7301. Min Act: -0.1700
Data Index: 2186935 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #19