Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3103 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6262. Min Range: -8.6262
Max Act: 8.6262. Min Act: -0.1700
Data Index: 4147212 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6262. Min Range: -8.6262
Max Act: 8.5012. Min Act: -0.1700
Data Index: 2012285 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6262. Min Range: -8.6262
Max Act: 8.5012. Min Act: -0.1700
Data Index: 3936849 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6262. Min Range: -8.6262
Max Act: 8.4387. Min Act: -0.1700
Data Index: 523868 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6262. Min Range: -8.6262
Max Act: 8.4387. Min Act: -0.1700
Data Index: 6697651 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6262. Min Range: -8.6262
Max Act: 8.3137. Min Act: -0.1700
Data Index: 8720487 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6262. Min Range: -8.6262
Max Act: 8.3137. Min Act: -0.1700
Data Index: 3773512 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6262. Min Range: -8.6262
Max Act: 8.3137. Min Act: -0.1700
Data Index: 3381639 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6262. Min Range: -8.6262
Max Act: 8.2512. Min Act: -0.1700
Data Index: 3308696 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6262. Min Range: -8.6262
Max Act: 8.1887. Min Act: -0.1700
Data Index: 11430 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6262. Min Range: -8.6262
Max Act: 8.1262. Min Act: -0.1700
Data Index: 7558290 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6262. Min Range: -8.6262
Max Act: 8.0949. Min Act: -0.1700
Data Index: 5364204 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6262. Min Range: -8.6262
Max Act: 8.0949. Min Act: -0.1700
Data Index: 1162915 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6262. Min Range: -8.6262
Max Act: 8.1262. Min Act: -0.1700
Data Index: 3240936 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6262. Min Range: -8.6262
Max Act: 8.1262. Min Act: -0.1700
Data Index: 6303065 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6262. Min Range: -8.6262
Max Act: 8.0637. Min Act: -0.1700
Data Index: 1338708 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6262. Min Range: -8.6262
Max Act: 8.0949. Min Act: -0.1700
Data Index: 5626424 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6262. Min Range: -8.6262
Max Act: 8.0324. Min Act: -0.1700
Data Index: 2330330 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6262. Min Range: -8.6262
Max Act: 7.9699. Min Act: -0.1700
Data Index: 4559323 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6262. Min Range: -8.6262
Max Act: 8.0012. Min Act: -0.1700
Data Index: 7867560 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #19