Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 925 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1949. Min Range: -6.1949
Max Act: 6.1949. Min Act: -0.1700
Data Index: 776551 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1949. Min Range: -6.1949
Max Act: 6.1636. Min Act: -0.1700
Data Index: 5292866 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1949. Min Range: -6.1949
Max Act: 6.1324. Min Act: -0.1700
Data Index: 6407638 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1949. Min Range: -6.1949
Max Act: 6.0699. Min Act: -0.1700
Data Index: 2407711 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1949. Min Range: -6.1949
Max Act: 6.0386. Min Act: -0.1700
Data Index: 5581319 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1949. Min Range: -6.1949
Max Act: 6.0386. Min Act: -0.1700
Data Index: 2258851 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1949. Min Range: -6.1949
Max Act: 6.0699. Min Act: -0.1700
Data Index: 8638674 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1949. Min Range: -6.1949
Max Act: 6.0074. Min Act: -0.1700
Data Index: 2851477 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1949. Min Range: -6.1949
Max Act: 6.0074. Min Act: -0.1700
Data Index: 2441991 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1949. Min Range: -6.1949
Max Act: 6.0074. Min Act: -0.1700
Data Index: 6915549 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1949. Min Range: -6.1949
Max Act: 6.0074. Min Act: -0.1700
Data Index: 896516 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1949. Min Range: -6.1949
Max Act: 5.9761. Min Act: -0.1695
Data Index: 8782389 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1949. Min Range: -6.1949
Max Act: 5.9761. Min Act: -0.1700
Data Index: 1178003 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1949. Min Range: -6.1949
Max Act: 5.9761. Min Act: -0.1700
Data Index: 3900695 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1949. Min Range: -6.1949
Max Act: 5.9761. Min Act: -0.1700
Data Index: 1660025 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1949. Min Range: -6.1949
Max Act: 5.9449. Min Act: -0.1700
Data Index: 2381170 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1949. Min Range: -6.1949
Max Act: 5.9449. Min Act: -0.1700
Data Index: 5178411 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1949. Min Range: -6.1949
Max Act: 5.9136. Min Act: -0.1700
Data Index: 5766646 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1949. Min Range: -6.1949
Max Act: 5.9449. Min Act: -0.1700
Data Index: 1077273 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1949. Min Range: -6.1949
Max Act: 5.9449. Min Act: -0.1699
Data Index: 765423 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #19