Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5887 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.1055. Min Range: -3.1055
Max Act: 3.0897. Min Act: -0.1700
Data Index: 3772730 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1055. Min Range: -3.1055
Max Act: 3.0897. Min Act: -0.1700
Data Index: 5328541 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1055. Min Range: -3.1055
Max Act: 3.1055. Min Act: -0.1700
Data Index: 8722911 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1055. Min Range: -3.1055
Max Act: 3.0581. Min Act: -0.1700
Data Index: 6667225 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1055. Min Range: -3.1055
Max Act: 3.0581. Min Act: -0.1700
Data Index: 836255 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1055. Min Range: -3.1055
Max Act: 3.0266. Min Act: -0.1700
Data Index: 1499340 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1055. Min Range: -3.1055
Max Act: 3.0424. Min Act: -0.1700
Data Index: 7448980 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1055. Min Range: -3.1055
Max Act: 3.0266. Min Act: -0.1700
Data Index: 7492418 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1055. Min Range: -3.1055
Max Act: 3.0266. Min Act: -0.1700
Data Index: 3753906 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1055. Min Range: -3.1055
Max Act: 3.0266. Min Act: -0.1700
Data Index: 322783 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1055. Min Range: -3.1055
Max Act: 3.0266. Min Act: -0.1700
Data Index: 6691515 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1055. Min Range: -3.1055
Max Act: 3.0266. Min Act: -0.1700
Data Index: 2167364 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1055. Min Range: -3.1055
Max Act: 3.0266. Min Act: -0.1700
Data Index: 5545067 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1055. Min Range: -3.1055
Max Act: 3.0266. Min Act: -0.1700
Data Index: 4129581 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1055. Min Range: -3.1055
Max Act: 3.0108. Min Act: -0.1700
Data Index: 5186289 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1055. Min Range: -3.1055
Max Act: 3.0108. Min Act: -0.1700
Data Index: 5259431 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1055. Min Range: -3.1055
Max Act: 3.0108. Min Act: -0.1700
Data Index: 1777577 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1055. Min Range: -3.1055
Max Act: 3.0108. Min Act: -0.1700
Data Index: 7296278 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1055. Min Range: -3.1055
Max Act: 3.0108. Min Act: -0.1700
Data Index: 5384351 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1055. Min Range: -3.1055
Max Act: 3.0108. Min Act: -0.1700
Data Index: 7339461 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #19