Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1734 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9740. Min Range: -6.9740
Max Act: 6.9740. Min Act: -0.1700
Data Index: 6750653 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9740. Min Range: -6.9740
Max Act: 6.8490. Min Act: -0.1700
Data Index: 3662009 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9740. Min Range: -6.9740
Max Act: 6.8490. Min Act: -0.1700
Data Index: 8695024 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9740. Min Range: -6.9740
Max Act: 6.8177. Min Act: -0.1700
Data Index: 735226 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9740. Min Range: -6.9740
Max Act: 6.7552. Min Act: -0.1700
Data Index: 3007702 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9740. Min Range: -6.9740
Max Act: 6.7552. Min Act: -0.1700
Data Index: 875729 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9740. Min Range: -6.9740
Max Act: 6.7552. Min Act: -0.1700
Data Index: 4989691 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9740. Min Range: -6.9740
Max Act: 6.7552. Min Act: -0.1700
Data Index: 8820257 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9740. Min Range: -6.9740
Max Act: 6.7552. Min Act: -0.1700
Data Index: 3645160 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9740. Min Range: -6.9740
Max Act: 6.7552. Min Act: -0.1700
Data Index: 1119020 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9740. Min Range: -6.9740
Max Act: 6.6927. Min Act: -0.1700
Data Index: 3766669 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9740. Min Range: -6.9740
Max Act: 6.7240. Min Act: -0.1700
Data Index: 920856 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9740. Min Range: -6.9740
Max Act: 6.6615. Min Act: -0.1700
Data Index: 594010 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9740. Min Range: -6.9740
Max Act: 6.6927. Min Act: -0.1700
Data Index: 1017232 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9740. Min Range: -6.9740
Max Act: 6.6927. Min Act: -0.1700
Data Index: 2988139 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9740. Min Range: -6.9740
Max Act: 6.6615. Min Act: -0.1700
Data Index: 5918428 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9740. Min Range: -6.9740
Max Act: 6.6615. Min Act: -0.1700
Data Index: 215865 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9740. Min Range: -6.9740
Max Act: 6.6302. Min Act: -0.1700
Data Index: 3437378 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9740. Min Range: -6.9740
Max Act: 6.6615. Min Act: -0.1700
Data Index: 4727470 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9740. Min Range: -6.9740
Max Act: 6.5990. Min Act: -0.1700
Data Index: 7497208 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #19