Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2906 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0183. Min Range: -4.0183
Max Act: 4.0183. Min Act: -0.1700
Data Index: 1811909 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0183. Min Range: -4.0183
Max Act: 4.0183. Min Act: -0.1700
Data Index: 1911481 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0183. Min Range: -4.0183
Max Act: 3.9871. Min Act: -0.1700
Data Index: 6068126 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0183. Min Range: -4.0183
Max Act: 3.9871. Min Act: -0.1700
Data Index: 8354715 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0183. Min Range: -4.0183
Max Act: 3.9871. Min Act: -0.1700
Data Index: 8307925 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0183. Min Range: -4.0183
Max Act: 3.9871. Min Act: -0.1700
Data Index: 4288808 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0183. Min Range: -4.0183
Max Act: 3.9871. Min Act: -0.1700
Data Index: 6442991 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0183. Min Range: -4.0183
Max Act: 3.9558. Min Act: -0.1700
Data Index: 6857722 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0183. Min Range: -4.0183
Max Act: 3.9558. Min Act: -0.1700
Data Index: 65834 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0183. Min Range: -4.0183
Max Act: 3.9558. Min Act: -0.1700
Data Index: 8304029 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0183. Min Range: -4.0183
Max Act: 3.9558. Min Act: -0.1700
Data Index: 6471380 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0183. Min Range: -4.0183
Max Act: 3.9871. Min Act: -0.1700
Data Index: 6207970 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0183. Min Range: -4.0183
Max Act: 3.8933. Min Act: -0.1700
Data Index: 195038 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0183. Min Range: -4.0183
Max Act: 3.8933. Min Act: -0.1700
Data Index: 6206996 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0183. Min Range: -4.0183
Max Act: 3.9246. Min Act: -0.1700
Data Index: 1073483 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0183. Min Range: -4.0183
Max Act: 3.8933. Min Act: -0.1700
Data Index: 4838504 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0183. Min Range: -4.0183
Max Act: 3.9558. Min Act: -0.1700
Data Index: 1086369 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0183. Min Range: -4.0183
Max Act: 3.9246. Min Act: -0.1700
Data Index: 5777040 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0183. Min Range: -4.0183
Max Act: 3.9246. Min Act: -0.1700
Data Index: 1255228 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0183. Min Range: -4.0183
Max Act: 3.9246. Min Act: -0.1700
Data Index: 5931305 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #19