Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3304 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9905. Min Range: -7.9905
Max Act: 7.9905. Min Act: -0.1700
Data Index: 436430 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9905. Min Range: -7.9905
Max Act: 7.8342. Min Act: -0.1700
Data Index: 4336242 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9905. Min Range: -7.9905
Max Act: 7.8967. Min Act: -0.1700
Data Index: 6363807 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9905. Min Range: -7.9905
Max Act: 7.7405. Min Act: -0.1700
Data Index: 7328713 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9905. Min Range: -7.9905
Max Act: 7.6780. Min Act: -0.1700
Data Index: 469261 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9905. Min Range: -7.9905
Max Act: 7.6780. Min Act: -0.1700
Data Index: 1982191 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9905. Min Range: -7.9905
Max Act: 7.6467. Min Act: -0.1700
Data Index: 983907 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9905. Min Range: -7.9905
Max Act: 7.4905. Min Act: -0.1700
Data Index: 8110585 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9905. Min Range: -7.9905
Max Act: 7.4592. Min Act: -0.1700
Data Index: 2166832 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9905. Min Range: -7.9905
Max Act: 7.4280. Min Act: -0.1700
Data Index: 4064072 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9905. Min Range: -7.9905
Max Act: 7.4280. Min Act: -0.1700
Data Index: 6138380 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9905. Min Range: -7.9905
Max Act: 7.3967. Min Act: -0.1700
Data Index: 7985385 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9905. Min Range: -7.9905
Max Act: 7.3655. Min Act: -0.1700
Data Index: 6452112 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9905. Min Range: -7.9905
Max Act: 7.3342. Min Act: -0.1700
Data Index: 5870292 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9905. Min Range: -7.9905
Max Act: 7.3342. Min Act: -0.1700
Data Index: 6641453 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9905. Min Range: -7.9905
Max Act: 7.3030. Min Act: -0.1700
Data Index: 832884 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9905. Min Range: -7.9905
Max Act: 7.3030. Min Act: -0.1700
Data Index: 8414776 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9905. Min Range: -7.9905
Max Act: 7.2717. Min Act: -0.1700
Data Index: 8094178 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9905. Min Range: -7.9905
Max Act: 7.2717. Min Act: -0.1700
Data Index: 3263731 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9905. Min Range: -7.9905
Max Act: 7.2092. Min Act: -0.1700
Data Index: 4878009 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #19