Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 348 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3900. Min Range: -6.3900
Max Act: 6.3900. Min Act: -0.1700
Data Index: 7600032 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3900. Min Range: -6.3900
Max Act: 6.1713. Min Act: -0.1700
Data Index: 2079052 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3900. Min Range: -6.3900
Max Act: 6.1713. Min Act: -0.1700
Data Index: 5122403 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3900. Min Range: -6.3900
Max Act: 6.0463. Min Act: -0.1700
Data Index: 5013621 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3900. Min Range: -6.3900
Max Act: 5.9525. Min Act: -0.1700
Data Index: 5622448 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3900. Min Range: -6.3900
Max Act: 5.8900. Min Act: -0.1700
Data Index: 7102552 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3900. Min Range: -6.3900
Max Act: 5.8900. Min Act: -0.1700
Data Index: 2869836 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3900. Min Range: -6.3900
Max Act: 5.8900. Min Act: -0.1700
Data Index: 2852213 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3900. Min Range: -6.3900
Max Act: 5.7650. Min Act: -0.1700
Data Index: 7927448 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3900. Min Range: -6.3900
Max Act: 5.7963. Min Act: -0.1700
Data Index: 7825584 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3900. Min Range: -6.3900
Max Act: 5.7650. Min Act: -0.1700
Data Index: 4578917 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3900. Min Range: -6.3900
Max Act: 5.7963. Min Act: -0.1700
Data Index: 1350659 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3900. Min Range: -6.3900
Max Act: 5.7650. Min Act: -0.1700
Data Index: 6006403 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3900. Min Range: -6.3900
Max Act: 5.7338. Min Act: -0.1700
Data Index: 6272217 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3900. Min Range: -6.3900
Max Act: 5.7025. Min Act: -0.1700
Data Index: 1059425 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3900. Min Range: -6.3900
Max Act: 5.7025. Min Act: -0.1700
Data Index: 3751301 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3900. Min Range: -6.3900
Max Act: 5.7025. Min Act: -0.1700
Data Index: 6485359 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3900. Min Range: -6.3900
Max Act: 5.6713. Min Act: -0.1700
Data Index: 18817 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3900. Min Range: -6.3900
Max Act: 5.6713. Min Act: -0.1700
Data Index: 3956531 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3900. Min Range: -6.3900
Max Act: 5.7025. Min Act: -0.1700
Data Index: 2546324 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #19