Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4646 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4918. Min Range: -6.4918
Max Act: 6.4918. Min Act: -0.1700
Data Index: 8754163 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4918. Min Range: -6.4918
Max Act: 6.2418. Min Act: -0.1700
Data Index: 1553446 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4918. Min Range: -6.4918
Max Act: 5.9606. Min Act: -0.1700
Data Index: 2180106 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4918. Min Range: -6.4918
Max Act: 5.9606. Min Act: -0.1700
Data Index: 1498264 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4918. Min Range: -6.4918
Max Act: 5.9293. Min Act: -0.1700
Data Index: 7919240 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4918. Min Range: -6.4918
Max Act: 5.8981. Min Act: -0.1700
Data Index: 2675156 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4918. Min Range: -6.4918
Max Act: 5.8668. Min Act: -0.1700
Data Index: 1815046 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4918. Min Range: -6.4918
Max Act: 5.8356. Min Act: -0.1700
Data Index: 146320 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4918. Min Range: -6.4918
Max Act: 5.8043. Min Act: -0.1700
Data Index: 8615720 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4918. Min Range: -6.4918
Max Act: 5.8043. Min Act: -0.1700
Data Index: 8516473 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4918. Min Range: -6.4918
Max Act: 5.7731. Min Act: -0.1700
Data Index: 168308 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4918. Min Range: -6.4918
Max Act: 5.7731. Min Act: -0.1700
Data Index: 7846868 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4918. Min Range: -6.4918
Max Act: 5.7731. Min Act: -0.1700
Data Index: 768277 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4918. Min Range: -6.4918
Max Act: 5.7731. Min Act: -0.1700
Data Index: 7480851 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4918. Min Range: -6.4918
Max Act: 5.7731. Min Act: -0.1700
Data Index: 5540280 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4918. Min Range: -6.4918
Max Act: 5.7418. Min Act: -0.1700
Data Index: 5718389 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4918. Min Range: -6.4918
Max Act: 5.7731. Min Act: -0.1700
Data Index: 5816156 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4918. Min Range: -6.4918
Max Act: 5.7418. Min Act: -0.1700
Data Index: 6346987 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4918. Min Range: -6.4918
Max Act: 5.7418. Min Act: -0.1700
Data Index: 1233457 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4918. Min Range: -6.4918
Max Act: 5.7106. Min Act: -0.1700
Data Index: 4876777 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #19