Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5113 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7871. Min Range: -8.7871
Max Act: 8.7871. Min Act: -0.1700
Data Index: 5195290 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7871. Min Range: -8.7871
Max Act: 8.6621. Min Act: -0.1700
Data Index: 4428150 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7871. Min Range: -8.7871
Max Act: 8.5996. Min Act: -0.1700
Data Index: 3040070 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7871. Min Range: -8.7871
Max Act: 8.5996. Min Act: -0.1700
Data Index: 6078356 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7871. Min Range: -8.7871
Max Act: 8.4746. Min Act: -0.1700
Data Index: 3087996 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7871. Min Range: -8.7871
Max Act: 8.5371. Min Act: -0.1700
Data Index: 4570773 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7871. Min Range: -8.7871
Max Act: 8.4121. Min Act: -0.1700
Data Index: 4060929 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7871. Min Range: -8.7871
Max Act: 8.3496. Min Act: -0.1700
Data Index: 8218240 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7871. Min Range: -8.7871
Max Act: 8.2871. Min Act: -0.1700
Data Index: 3914575 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7871. Min Range: -8.7871
Max Act: 8.1934. Min Act: -0.1700
Data Index: 7107294 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7871. Min Range: -8.7871
Max Act: 8.2246. Min Act: -0.1700
Data Index: 7911568 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7871. Min Range: -8.7871
Max Act: 8.2246. Min Act: -0.1700
Data Index: 7672008 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7871. Min Range: -8.7871
Max Act: 8.2246. Min Act: -0.1700
Data Index: 4774838 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7871. Min Range: -8.7871
Max Act: 8.1621. Min Act: -0.1700
Data Index: 2799540 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7871. Min Range: -8.7871
Max Act: 8.0996. Min Act: -0.1700
Data Index: 4407199 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7871. Min Range: -8.7871
Max Act: 8.1309. Min Act: -0.1700
Data Index: 7679109 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7871. Min Range: -8.7871
Max Act: 8.1309. Min Act: -0.1700
Data Index: 1860744 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7871. Min Range: -8.7871
Max Act: 8.0996. Min Act: -0.1700
Data Index: 6864880 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7871. Min Range: -8.7871
Max Act: 8.0684. Min Act: -0.1700
Data Index: 3487815 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7871. Min Range: -8.7871
Max Act: 8.0684. Min Act: -0.1700
Data Index: 88930 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #19