Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2802 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5871. Min Range: -5.5871
Max Act: 5.5871. Min Act: -0.1700
Data Index: 6441897 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5871. Min Range: -5.5871
Max Act: 5.3683. Min Act: -0.1700
Data Index: 443227 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5871. Min Range: -5.5871
Max Act: 5.3371. Min Act: -0.1700
Data Index: 6805383 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5871. Min Range: -5.5871
Max Act: 5.3058. Min Act: -0.1700
Data Index: 266875 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5871. Min Range: -5.5871
Max Act: 5.2746. Min Act: -0.1700
Data Index: 5246922 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5871. Min Range: -5.5871
Max Act: 5.2746. Min Act: -0.1700
Data Index: 1271611 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5871. Min Range: -5.5871
Max Act: 5.2121. Min Act: -0.1700
Data Index: 2788155 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5871. Min Range: -5.5871
Max Act: 5.1808. Min Act: -0.1700
Data Index: 7252528 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5871. Min Range: -5.5871
Max Act: 5.1808. Min Act: -0.1700
Data Index: 8603777 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5871. Min Range: -5.5871
Max Act: 5.1496. Min Act: -0.1700
Data Index: 856891 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5871. Min Range: -5.5871
Max Act: 5.1496. Min Act: -0.1700
Data Index: 5514693 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5871. Min Range: -5.5871
Max Act: 5.1496. Min Act: -0.1700
Data Index: 2391319 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5871. Min Range: -5.5871
Max Act: 5.1496. Min Act: -0.1700
Data Index: 2858876 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5871. Min Range: -5.5871
Max Act: 5.1183. Min Act: -0.1700
Data Index: 6862155 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5871. Min Range: -5.5871
Max Act: 5.1183. Min Act: -0.1700
Data Index: 4239061 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5871. Min Range: -5.5871
Max Act: 5.0871. Min Act: -0.1700
Data Index: 7831304 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5871. Min Range: -5.5871
Max Act: 5.1496. Min Act: -0.1700
Data Index: 295141 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5871. Min Range: -5.5871
Max Act: 5.0871. Min Act: -0.1700
Data Index: 1914722 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5871. Min Range: -5.5871
Max Act: 5.0871. Min Act: -0.1700
Data Index: 5524232 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5871. Min Range: -5.5871
Max Act: 5.0871. Min Act: -0.1700
Data Index: 1927338 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #19