Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1693 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8541. Min Range: -4.8541
Max Act: 4.8541. Min Act: -0.1700
Data Index: 8811433 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8541. Min Range: -4.8541
Max Act: 4.7291. Min Act: -0.1700
Data Index: 8333707 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8541. Min Range: -4.8541
Max Act: 4.6979. Min Act: -0.1700
Data Index: 3548403 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8541. Min Range: -4.8541
Max Act: 4.6666. Min Act: -0.1700
Data Index: 2694333 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8541. Min Range: -4.8541
Max Act: 4.6666. Min Act: -0.1700
Data Index: 7035531 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8541. Min Range: -4.8541
Max Act: 4.6354. Min Act: -0.1700
Data Index: 8589269 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8541. Min Range: -4.8541
Max Act: 4.6354. Min Act: -0.1700
Data Index: 6789928 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8541. Min Range: -4.8541
Max Act: 4.6354. Min Act: -0.1700
Data Index: 6881789 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8541. Min Range: -4.8541
Max Act: 4.5729. Min Act: -0.1700
Data Index: 4622074 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8541. Min Range: -4.8541
Max Act: 4.5729. Min Act: -0.1700
Data Index: 5664546 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8541. Min Range: -4.8541
Max Act: 4.5729. Min Act: -0.1700
Data Index: 6951832 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8541. Min Range: -4.8541
Max Act: 4.5416. Min Act: -0.1700
Data Index: 7582350 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8541. Min Range: -4.8541
Max Act: 4.6041. Min Act: -0.1700
Data Index: 7140868 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8541. Min Range: -4.8541
Max Act: 4.5729. Min Act: -0.1700
Data Index: 8127990 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8541. Min Range: -4.8541
Max Act: 4.5416. Min Act: -0.1700
Data Index: 2042806 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8541. Min Range: -4.8541
Max Act: 4.5416. Min Act: -0.1700
Data Index: 7082760 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8541. Min Range: -4.8541
Max Act: 4.5416. Min Act: -0.1700
Data Index: 8800271 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8541. Min Range: -4.8541
Max Act: 4.5104. Min Act: -0.1700
Data Index: 5640771 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8541. Min Range: -4.8541
Max Act: 4.5104. Min Act: -0.1700
Data Index: 4132575 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8541. Min Range: -4.8541
Max Act: 4.5104. Min Act: -0.1700
Data Index: 2136504 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #19