Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3597 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1918. Min Range: -8.1918
Max Act: 8.1918. Min Act: -0.1700
Data Index: 5282232 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1918. Min Range: -8.1918
Max Act: 8.0043. Min Act: -0.1700
Data Index: 6207832 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1918. Min Range: -8.1918
Max Act: 7.9418. Min Act: -0.1700
Data Index: 2908680 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1918. Min Range: -8.1918
Max Act: 7.8481. Min Act: -0.1700
Data Index: 2390682 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1918. Min Range: -8.1918
Max Act: 7.8481. Min Act: -0.1700
Data Index: 2652331 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1918. Min Range: -8.1918
Max Act: 7.7856. Min Act: -0.1700
Data Index: 2625415 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1918. Min Range: -8.1918
Max Act: 7.6293. Min Act: -0.1700
Data Index: 8524233 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1918. Min Range: -8.1918
Max Act: 7.6293. Min Act: -0.1700
Data Index: 6879298 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1918. Min Range: -8.1918
Max Act: 7.5981. Min Act: -0.1700
Data Index: 2095161 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1918. Min Range: -8.1918
Max Act: 7.5356. Min Act: -0.1700
Data Index: 5235005 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1918. Min Range: -8.1918
Max Act: 7.5356. Min Act: -0.1700
Data Index: 228777 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1918. Min Range: -8.1918
Max Act: 7.5043. Min Act: -0.1700
Data Index: 3514711 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1918. Min Range: -8.1918
Max Act: 7.4106. Min Act: -0.1700
Data Index: 5213675 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1918. Min Range: -8.1918
Max Act: 7.3793. Min Act: -0.1700
Data Index: 8701462 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1918. Min Range: -8.1918
Max Act: 7.3481. Min Act: -0.1700
Data Index: 2572308 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1918. Min Range: -8.1918
Max Act: 7.2543. Min Act: -0.1700
Data Index: 7444153 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1918. Min Range: -8.1918
Max Act: 7.2231. Min Act: -0.1700
Data Index: 2682002 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1918. Min Range: -8.1918
Max Act: 7.2543. Min Act: -0.1700
Data Index: 5359601 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1918. Min Range: -8.1918
Max Act: 7.1606. Min Act: -0.1700
Data Index: 2566740 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1918. Min Range: -8.1918
Max Act: 7.1606. Min Act: -0.1700
Data Index: 5983427 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #19