Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3381 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0282. Min Range: -6.0282
Max Act: 6.0282. Min Act: -0.1700
Data Index: 7189647 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0282. Min Range: -6.0282
Max Act: 5.9657. Min Act: -0.1700
Data Index: 3064520 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0282. Min Range: -6.0282
Max Act: 5.9032. Min Act: -0.1700
Data Index: 4952251 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0282. Min Range: -6.0282
Max Act: 5.8407. Min Act: -0.1700
Data Index: 634658 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0282. Min Range: -6.0282
Max Act: 5.8094. Min Act: -0.1700
Data Index: 3052756 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0282. Min Range: -6.0282
Max Act: 5.7782. Min Act: -0.1700
Data Index: 2150783 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0282. Min Range: -6.0282
Max Act: 5.7782. Min Act: -0.1700
Data Index: 2885367 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0282. Min Range: -6.0282
Max Act: 5.7157. Min Act: -0.1700
Data Index: 7462831 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0282. Min Range: -6.0282
Max Act: 5.7157. Min Act: -0.1700
Data Index: 4682172 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0282. Min Range: -6.0282
Max Act: 5.6844. Min Act: -0.1700
Data Index: 2352462 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0282. Min Range: -6.0282
Max Act: 5.6844. Min Act: -0.1700
Data Index: 5290159 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0282. Min Range: -6.0282
Max Act: 5.6532. Min Act: -0.1700
Data Index: 8614267 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0282. Min Range: -6.0282
Max Act: 5.6532. Min Act: -0.1700
Data Index: 6365704 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0282. Min Range: -6.0282
Max Act: 5.6219. Min Act: -0.1700
Data Index: 7999216 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0282. Min Range: -6.0282
Max Act: 5.6219. Min Act: -0.1700
Data Index: 8600038 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0282. Min Range: -6.0282
Max Act: 5.6219. Min Act: -0.1700
Data Index: 2096649 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0282. Min Range: -6.0282
Max Act: 5.6219. Min Act: -0.1700
Data Index: 4899718 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0282. Min Range: -6.0282
Max Act: 5.6219. Min Act: -0.1700
Data Index: 3969459 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0282. Min Range: -6.0282
Max Act: 5.5907. Min Act: -0.1700
Data Index: 7591100 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0282. Min Range: -6.0282
Max Act: 5.5907. Min Act: -0.1700
Data Index: 255306 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #19