Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1269 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1479. Min Range: -7.1479
Max Act: 7.1479. Min Act: -0.1700
Data Index: 2299792 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1479. Min Range: -7.1479
Max Act: 6.9291. Min Act: -0.1700
Data Index: 7648495 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1479. Min Range: -7.1479
Max Act: 6.8354. Min Act: -0.1700
Data Index: 120567 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1479. Min Range: -7.1479
Max Act: 6.8354. Min Act: -0.1700
Data Index: 2978876 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1479. Min Range: -7.1479
Max Act: 6.7729. Min Act: -0.1700
Data Index: 2397784 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1479. Min Range: -7.1479
Max Act: 6.5854. Min Act: -0.1700
Data Index: 5684793 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1479. Min Range: -7.1479
Max Act: 6.6166. Min Act: -0.1700
Data Index: 2516701 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1479. Min Range: -7.1479
Max Act: 6.6166. Min Act: -0.1700
Data Index: 6020803 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1479. Min Range: -7.1479
Max Act: 6.5854. Min Act: -0.1700
Data Index: 2952034 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1479. Min Range: -7.1479
Max Act: 6.5854. Min Act: -0.1700
Data Index: 6812014 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1479. Min Range: -7.1479
Max Act: 6.5854. Min Act: -0.1700
Data Index: 5606736 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1479. Min Range: -7.1479
Max Act: 6.5229. Min Act: -0.1700
Data Index: 3500185 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1479. Min Range: -7.1479
Max Act: 6.5541. Min Act: -0.1700
Data Index: 3824656 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1479. Min Range: -7.1479
Max Act: 6.4916. Min Act: -0.1700
Data Index: 8048769 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1479. Min Range: -7.1479
Max Act: 6.4604. Min Act: -0.1700
Data Index: 177543 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1479. Min Range: -7.1479
Max Act: 6.4916. Min Act: -0.1700
Data Index: 6020813 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1479. Min Range: -7.1479
Max Act: 6.4916. Min Act: -0.1700
Data Index: 2257360 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1479. Min Range: -7.1479
Max Act: 6.4604. Min Act: -0.1700
Data Index: 1920194 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1479. Min Range: -7.1479
Max Act: 6.4604. Min Act: -0.1700
Data Index: 556149 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1479. Min Range: -7.1479
Max Act: 6.4604. Min Act: -0.1700
Data Index: 2428525 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #19