Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3443 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1249. Min Range: -5.1249
Max Act: 5.1249. Min Act: -0.1700
Data Index: 3531677 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1249. Min Range: -5.1249
Max Act: 4.9999. Min Act: -0.1700
Data Index: 6007183 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1249. Min Range: -5.1249
Max Act: 4.9686. Min Act: -0.1700
Data Index: 2361610 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1249. Min Range: -5.1249
Max Act: 4.9061. Min Act: -0.1700
Data Index: 8675055 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1249. Min Range: -5.1249
Max Act: 4.9374. Min Act: -0.1700
Data Index: 3208433 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1249. Min Range: -5.1249
Max Act: 4.9061. Min Act: -0.1700
Data Index: 3851426 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1249. Min Range: -5.1249
Max Act: 4.9374. Min Act: -0.1700
Data Index: 2671124 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1249. Min Range: -5.1249
Max Act: 4.8436. Min Act: -0.1700
Data Index: 6547158 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1249. Min Range: -5.1249
Max Act: 4.8124. Min Act: -0.1700
Data Index: 3101144 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1249. Min Range: -5.1249
Max Act: 4.8124. Min Act: -0.1700
Data Index: 6963702 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1249. Min Range: -5.1249
Max Act: 4.8124. Min Act: -0.1700
Data Index: 5288595 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1249. Min Range: -5.1249
Max Act: 4.8124. Min Act: -0.1700
Data Index: 7442938 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1249. Min Range: -5.1249
Max Act: 4.7811. Min Act: -0.1700
Data Index: 6528573 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1249. Min Range: -5.1249
Max Act: 4.7499. Min Act: -0.1700
Data Index: 8006680 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1249. Min Range: -5.1249
Max Act: 4.6874. Min Act: -0.1700
Data Index: 547530 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1249. Min Range: -5.1249
Max Act: 4.7186. Min Act: -0.1700
Data Index: 4423107 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1249. Min Range: -5.1249
Max Act: 4.7186. Min Act: -0.1700
Data Index: 3116165 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1249. Min Range: -5.1249
Max Act: 4.7186. Min Act: -0.1700
Data Index: 2994439 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1249. Min Range: -5.1249
Max Act: 4.7186. Min Act: -0.1700
Data Index: 914403 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1249. Min Range: -5.1249
Max Act: 4.7186. Min Act: -0.1700
Data Index: 3327788 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #19