Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4970 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9945. Min Range: -5.9945
Max Act: 5.9945. Min Act: -0.1700
Data Index: 4110669 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9945. Min Range: -5.9945
Max Act: 5.9633. Min Act: -0.1700
Data Index: 7187792 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9945. Min Range: -5.9945
Max Act: 5.7758. Min Act: -0.1700
Data Index: 2248552 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9945. Min Range: -5.9945
Max Act: 5.7445. Min Act: -0.1700
Data Index: 3512989 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9945. Min Range: -5.9945
Max Act: 5.6195. Min Act: -0.1700
Data Index: 969484 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9945. Min Range: -5.9945
Max Act: 5.5883. Min Act: -0.1700
Data Index: 8580528 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9945. Min Range: -5.9945
Max Act: 5.5570. Min Act: -0.1700
Data Index: 8499665 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9945. Min Range: -5.9945
Max Act: 5.5570. Min Act: -0.1700
Data Index: 464946 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9945. Min Range: -5.9945
Max Act: 5.5258. Min Act: -0.1700
Data Index: 5255414 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9945. Min Range: -5.9945
Max Act: 5.5258. Min Act: -0.1700
Data Index: 879888 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9945. Min Range: -5.9945
Max Act: 5.5258. Min Act: -0.1700
Data Index: 2934729 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9945. Min Range: -5.9945
Max Act: 5.5570. Min Act: -0.1700
Data Index: 6951540 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9945. Min Range: -5.9945
Max Act: 5.4633. Min Act: -0.1700
Data Index: 6491901 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9945. Min Range: -5.9945
Max Act: 5.4945. Min Act: -0.1700
Data Index: 136780 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9945. Min Range: -5.9945
Max Act: 5.4945. Min Act: -0.1700
Data Index: 8500497 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9945. Min Range: -5.9945
Max Act: 5.4320. Min Act: -0.1700
Data Index: 5792169 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9945. Min Range: -5.9945
Max Act: 5.4633. Min Act: -0.1700
Data Index: 344654 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9945. Min Range: -5.9945
Max Act: 5.4633. Min Act: -0.1700
Data Index: 7735619 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9945. Min Range: -5.9945
Max Act: 5.4633. Min Act: -0.1700
Data Index: 161753 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9945. Min Range: -5.9945
Max Act: 5.4633. Min Act: -0.1700
Data Index: 6918999 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #19