Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3382 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.7189. Min Range: -1.7189
Max Act: 1.7189. Min Act: -0.1700
Data Index: 5780250 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7189. Min Range: -1.7189
Max Act: 1.6581. Min Act: -0.1700
Data Index: 7738486 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7189. Min Range: -1.7189
Max Act: 1.6581. Min Act: -0.1700
Data Index: 7270963 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7189. Min Range: -1.7189
Max Act: 1.6494. Min Act: -0.1700
Data Index: 4156655 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7189. Min Range: -1.7189
Max Act: 1.6059. Min Act: -0.1700
Data Index: 1818765 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7189. Min Range: -1.7189
Max Act: 1.5884. Min Act: -0.1700
Data Index: 3275152 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7189. Min Range: -1.7189
Max Act: 1.5884. Min Act: -0.1700
Data Index: 7929140 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7189. Min Range: -1.7189
Max Act: 1.5796. Min Act: -0.1700
Data Index: 2352013 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7189. Min Range: -1.7189
Max Act: 1.5796. Min Act: -0.1700
Data Index: 795796 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7189. Min Range: -1.7189
Max Act: 1.5709. Min Act: -0.1700
Data Index: 5208224 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7189. Min Range: -1.7189
Max Act: 1.5622. Min Act: -0.1700
Data Index: 875997 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7189. Min Range: -1.7189
Max Act: 1.5622. Min Act: -0.1700
Data Index: 3736795 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7189. Min Range: -1.7189
Max Act: 1.5622. Min Act: -0.1700
Data Index: 2010732 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7189. Min Range: -1.7189
Max Act: 1.5534. Min Act: -0.1700
Data Index: 3480950 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7189. Min Range: -1.7189
Max Act: 1.5534. Min Act: -0.1700
Data Index: 2840946 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7189. Min Range: -1.7189
Max Act: 1.5534. Min Act: -0.1700
Data Index: 4617100 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7189. Min Range: -1.7189
Max Act: 1.5534. Min Act: -0.1699
Data Index: 150296 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7189. Min Range: -1.7189
Max Act: 1.5534. Min Act: -0.1700
Data Index: 5872814 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7189. Min Range: -1.7189
Max Act: 1.5446. Min Act: -0.1700
Data Index: 4668157 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7189. Min Range: -1.7189
Max Act: 1.5446. Min Act: -0.1700
Data Index: 7907897 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #19