Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 766 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8022. Min Range: -6.8022
Max Act: 6.8022. Min Act: -0.1700
Data Index: 25233 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8022. Min Range: -6.8022
Max Act: 6.6147. Min Act: -0.1700
Data Index: 5300892 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8022. Min Range: -6.8022
Max Act: 6.4897. Min Act: -0.1700
Data Index: 5567309 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8022. Min Range: -6.8022
Max Act: 6.3959. Min Act: -0.1700
Data Index: 968642 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8022. Min Range: -6.8022
Max Act: 6.3647. Min Act: -0.1700
Data Index: 8422866 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8022. Min Range: -6.8022
Max Act: 6.3022. Min Act: -0.1700
Data Index: 6044853 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8022. Min Range: -6.8022
Max Act: 6.3334. Min Act: -0.1700
Data Index: 3021039 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8022. Min Range: -6.8022
Max Act: 6.3022. Min Act: -0.1700
Data Index: 8670320 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8022. Min Range: -6.8022
Max Act: 6.2709. Min Act: -0.1700
Data Index: 6001792 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8022. Min Range: -6.8022
Max Act: 6.2709. Min Act: -0.1700
Data Index: 4714452 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8022. Min Range: -6.8022
Max Act: 6.2397. Min Act: -0.1700
Data Index: 892757 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8022. Min Range: -6.8022
Max Act: 6.2084. Min Act: -0.1700
Data Index: 2669808 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8022. Min Range: -6.8022
Max Act: 6.2084. Min Act: -0.1700
Data Index: 2223058 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8022. Min Range: -6.8022
Max Act: 6.1772. Min Act: -0.1700
Data Index: 6073859 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8022. Min Range: -6.8022
Max Act: 6.1459. Min Act: -0.1700
Data Index: 2474817 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8022. Min Range: -6.8022
Max Act: 6.2084. Min Act: -0.1700
Data Index: 5096167 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8022. Min Range: -6.8022
Max Act: 6.1459. Min Act: -0.1700
Data Index: 6543292 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8022. Min Range: -6.8022
Max Act: 6.1459. Min Act: -0.1700
Data Index: 1604827 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8022. Min Range: -6.8022
Max Act: 6.1459. Min Act: -0.1700
Data Index: 1215933 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8022. Min Range: -6.8022
Max Act: 6.1459. Min Act: -0.1700
Data Index: 6227981 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #19