Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2958 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9615. Min Range: -5.9615
Max Act: 5.9615. Min Act: -0.1700
Data Index: 1622698 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9615. Min Range: -5.9615
Max Act: 5.8365. Min Act: -0.1700
Data Index: 254979 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9615. Min Range: -5.9615
Max Act: 5.7115. Min Act: -0.1700
Data Index: 4943835 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9615. Min Range: -5.9615
Max Act: 5.6490. Min Act: -0.1700
Data Index: 1328037 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9615. Min Range: -5.9615
Max Act: 5.6803. Min Act: -0.1700
Data Index: 3081565 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9615. Min Range: -5.9615
Max Act: 5.6490. Min Act: -0.1700
Data Index: 4708484 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9615. Min Range: -5.9615
Max Act: 5.6178. Min Act: -0.1700
Data Index: 5655820 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9615. Min Range: -5.9615
Max Act: 5.6178. Min Act: -0.1700
Data Index: 4491983 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9615. Min Range: -5.9615
Max Act: 5.5865. Min Act: -0.1700
Data Index: 2460934 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9615. Min Range: -5.9615
Max Act: 5.5240. Min Act: -0.1700
Data Index: 3839896 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9615. Min Range: -5.9615
Max Act: 5.5553. Min Act: -0.1700
Data Index: 7468773 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9615. Min Range: -5.9615
Max Act: 5.5553. Min Act: -0.1700
Data Index: 644356 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9615. Min Range: -5.9615
Max Act: 5.5240. Min Act: -0.1700
Data Index: 180678 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9615. Min Range: -5.9615
Max Act: 5.5240. Min Act: -0.1700
Data Index: 3663716 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9615. Min Range: -5.9615
Max Act: 5.5240. Min Act: -0.1700
Data Index: 7687328 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9615. Min Range: -5.9615
Max Act: 5.4928. Min Act: -0.1700
Data Index: 4693887 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9615. Min Range: -5.9615
Max Act: 5.5240. Min Act: -0.1700
Data Index: 5648824 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9615. Min Range: -5.9615
Max Act: 5.4928. Min Act: -0.1700
Data Index: 5209301 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9615. Min Range: -5.9615
Max Act: 5.4928. Min Act: -0.1700
Data Index: 1196267 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9615. Min Range: -5.9615
Max Act: 5.4928. Min Act: -0.1700
Data Index: 2637837 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #19