Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1703 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3850. Min Range: -7.3850
Max Act: 7.3850. Min Act: -0.1700
Data Index: 1364157 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3850. Min Range: -7.3850
Max Act: 7.1975. Min Act: -0.1700
Data Index: 5915338 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3850. Min Range: -7.3850
Max Act: 6.8850. Min Act: -0.1700
Data Index: 3683388 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3850. Min Range: -7.3850
Max Act: 6.9163. Min Act: -0.1700
Data Index: 279609 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3850. Min Range: -7.3850
Max Act: 6.8225. Min Act: -0.1700
Data Index: 6256959 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3850. Min Range: -7.3850
Max Act: 6.7913. Min Act: -0.1700
Data Index: 2318123 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3850. Min Range: -7.3850
Max Act: 6.7913. Min Act: -0.1700
Data Index: 5915337 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3850. Min Range: -7.3850
Max Act: 6.7600. Min Act: -0.1700
Data Index: 2530913 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3850. Min Range: -7.3850
Max Act: 6.7600. Min Act: -0.1700
Data Index: 5050061 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3850. Min Range: -7.3850
Max Act: 6.7288. Min Act: -0.1700
Data Index: 7786016 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3850. Min Range: -7.3850
Max Act: 6.7288. Min Act: -0.1700
Data Index: 8694079 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3850. Min Range: -7.3850
Max Act: 6.6975. Min Act: -0.1700
Data Index: 7701174 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3850. Min Range: -7.3850
Max Act: 6.6663. Min Act: -0.1700
Data Index: 4493809 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3850. Min Range: -7.3850
Max Act: 6.6975. Min Act: -0.1700
Data Index: 3610816 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3850. Min Range: -7.3850
Max Act: 6.6663. Min Act: -0.1700
Data Index: 1166155 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3850. Min Range: -7.3850
Max Act: 6.6350. Min Act: -0.1700
Data Index: 3137513 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3850. Min Range: -7.3850
Max Act: 6.6350. Min Act: -0.1700
Data Index: 6342169 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3850. Min Range: -7.3850
Max Act: 6.6350. Min Act: -0.1700
Data Index: 4526111 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3850. Min Range: -7.3850
Max Act: 6.6663. Min Act: -0.1700
Data Index: 1546985 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3850. Min Range: -7.3850
Max Act: 6.6350. Min Act: -0.1700
Data Index: 5292232 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #19