Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 478 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3918. Min Range: -6.3918
Max Act: 6.3918. Min Act: -0.1700
Data Index: 7504 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3918. Min Range: -6.3918
Max Act: 6.3918. Min Act: -0.1700
Data Index: 1679310 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3918. Min Range: -6.3918
Max Act: 6.0793. Min Act: -0.1700
Data Index: 6481318 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3918. Min Range: -6.3918
Max Act: 6.0793. Min Act: -0.1700
Data Index: 2869121 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3918. Min Range: -6.3918
Max Act: 5.9855. Min Act: -0.1700
Data Index: 6953326 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3918. Min Range: -6.3918
Max Act: 5.9230. Min Act: -0.1700
Data Index: 8490842 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3918. Min Range: -6.3918
Max Act: 5.8918. Min Act: -0.1700
Data Index: 6023679 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3918. Min Range: -6.3918
Max Act: 5.8605. Min Act: -0.1700
Data Index: 2631706 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3918. Min Range: -6.3918
Max Act: 5.8293. Min Act: -0.1700
Data Index: 861098 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3918. Min Range: -6.3918
Max Act: 5.8605. Min Act: -0.1700
Data Index: 2933753 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3918. Min Range: -6.3918
Max Act: 5.8293. Min Act: -0.1700
Data Index: 3542393 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3918. Min Range: -6.3918
Max Act: 5.8293. Min Act: -0.1700
Data Index: 2598403 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3918. Min Range: -6.3918
Max Act: 5.7980. Min Act: -0.1700
Data Index: 5955010 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3918. Min Range: -6.3918
Max Act: 5.8293. Min Act: -0.1700
Data Index: 6754087 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3918. Min Range: -6.3918
Max Act: 5.7980. Min Act: -0.1700
Data Index: 8083371 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3918. Min Range: -6.3918
Max Act: 5.7980. Min Act: -0.1700
Data Index: 7262648 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3918. Min Range: -6.3918
Max Act: 5.7668. Min Act: -0.1700
Data Index: 2746236 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3918. Min Range: -6.3918
Max Act: 5.7355. Min Act: -0.1700
Data Index: 6595593 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3918. Min Range: -6.3918
Max Act: 5.7668. Min Act: -0.1700
Data Index: 2553084 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3918. Min Range: -6.3918
Max Act: 5.7668. Min Act: -0.1700
Data Index: 5783964 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #19