Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5140 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8788. Min Range: -6.8788
Max Act: 6.8788. Min Act: -0.1700
Data Index: 8438187 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8788. Min Range: -6.8788
Max Act: 6.8788. Min Act: -0.1700
Data Index: 2506780 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8788. Min Range: -6.8788
Max Act: 6.8163. Min Act: -0.1700
Data Index: 1494471 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8788. Min Range: -6.8788
Max Act: 6.7851. Min Act: -0.1700
Data Index: 6484497 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8788. Min Range: -6.8788
Max Act: 6.7851. Min Act: -0.1700
Data Index: 1052933 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8788. Min Range: -6.8788
Max Act: 6.6913. Min Act: -0.1700
Data Index: 166790 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8788. Min Range: -6.8788
Max Act: 6.6913. Min Act: -0.1700
Data Index: 1193456 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8788. Min Range: -6.8788
Max Act: 6.6601. Min Act: -0.1700
Data Index: 3168468 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8788. Min Range: -6.8788
Max Act: 6.6288. Min Act: -0.1700
Data Index: 6102318 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8788. Min Range: -6.8788
Max Act: 6.5976. Min Act: -0.1700
Data Index: 7728742 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8788. Min Range: -6.8788
Max Act: 6.6601. Min Act: -0.1700
Data Index: 5740322 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8788. Min Range: -6.8788
Max Act: 6.5663. Min Act: -0.1700
Data Index: 4461683 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8788. Min Range: -6.8788
Max Act: 6.5351. Min Act: -0.1700
Data Index: 4316489 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8788. Min Range: -6.8788
Max Act: 6.5351. Min Act: -0.1700
Data Index: 5940984 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8788. Min Range: -6.8788
Max Act: 6.5038. Min Act: -0.1700
Data Index: 3334146 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8788. Min Range: -6.8788
Max Act: 6.4726. Min Act: -0.1700
Data Index: 8040521 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8788. Min Range: -6.8788
Max Act: 6.5038. Min Act: -0.1700
Data Index: 4077510 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8788. Min Range: -6.8788
Max Act: 6.5038. Min Act: -0.1700
Data Index: 223838 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8788. Min Range: -6.8788
Max Act: 6.4726. Min Act: -0.1700
Data Index: 2698863 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8788. Min Range: -6.8788
Max Act: 6.5038. Min Act: -0.1700
Data Index: 6564701 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #19