Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3436 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 10.0129. Min Range: -10.0129
Max Act: 10.0129. Min Act: -0.1700
Data Index: 7462199 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.0129. Min Range: -10.0129
Max Act: 10.0129. Min Act: -0.1700
Data Index: 353416 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.0129. Min Range: -10.0129
Max Act: 10.0129. Min Act: -0.1700
Data Index: 105959 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.0129. Min Range: -10.0129
Max Act: 9.9504. Min Act: -0.1700
Data Index: 5858486 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.0129. Min Range: -10.0129
Max Act: 9.9504. Min Act: -0.1700
Data Index: 5949873 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.0129. Min Range: -10.0129
Max Act: 9.9504. Min Act: -0.1700
Data Index: 7010989 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.0129. Min Range: -10.0129
Max Act: 9.9504. Min Act: -0.1700
Data Index: 1600405 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.0129. Min Range: -10.0129
Max Act: 9.8254. Min Act: -0.1700
Data Index: 705497 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.0129. Min Range: -10.0129
Max Act: 9.8254. Min Act: -0.1700
Data Index: 1340177 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.0129. Min Range: -10.0129
Max Act: 9.8879. Min Act: -0.1700
Data Index: 3156474 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.0129. Min Range: -10.0129
Max Act: 9.8879. Min Act: -0.1700
Data Index: 8570386 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.0129. Min Range: -10.0129
Max Act: 9.8879. Min Act: -0.1700
Data Index: 389465 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.0129. Min Range: -10.0129
Max Act: 9.8254. Min Act: -0.1700
Data Index: 721166 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.0129. Min Range: -10.0129
Max Act: 9.8254. Min Act: -0.1700
Data Index: 5551625 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.0129. Min Range: -10.0129
Max Act: 9.8254. Min Act: -0.1700
Data Index: 7863985 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.0129. Min Range: -10.0129
Max Act: 9.8254. Min Act: -0.1700
Data Index: 644250 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.0129. Min Range: -10.0129
Max Act: 9.7629. Min Act: -0.1700
Data Index: 917852 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.0129. Min Range: -10.0129
Max Act: 9.8254. Min Act: -0.1700
Data Index: 7706746 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.0129. Min Range: -10.0129
Max Act: 9.8254. Min Act: -0.1700
Data Index: 4170660 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.0129. Min Range: -10.0129
Max Act: 9.8879. Min Act: -0.1700
Data Index: 8628536 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #19