Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5476 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5792. Min Range: -6.5792
Max Act: 6.5792. Min Act: -0.1700
Data Index: 1114194 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5792. Min Range: -6.5792
Max Act: 6.5792. Min Act: -0.1700
Data Index: 5130462 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5792. Min Range: -6.5792
Max Act: 6.5167. Min Act: -0.1700
Data Index: 6925009 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5792. Min Range: -6.5792
Max Act: 6.5167. Min Act: -0.1700
Data Index: 7752283 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5792. Min Range: -6.5792
Max Act: 6.4854. Min Act: -0.1700
Data Index: 703656 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5792. Min Range: -6.5792
Max Act: 6.3917. Min Act: -0.1700
Data Index: 4678360 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5792. Min Range: -6.5792
Max Act: 6.3604. Min Act: -0.1700
Data Index: 4080762 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5792. Min Range: -6.5792
Max Act: 6.3292. Min Act: -0.1700
Data Index: 5897697 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5792. Min Range: -6.5792
Max Act: 6.3292. Min Act: -0.1700
Data Index: 5307456 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5792. Min Range: -6.5792
Max Act: 6.2667. Min Act: -0.1700
Data Index: 833457 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5792. Min Range: -6.5792
Max Act: 6.2667. Min Act: -0.1700
Data Index: 8304910 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5792. Min Range: -6.5792
Max Act: 6.2667. Min Act: -0.1700
Data Index: 2332915 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5792. Min Range: -6.5792
Max Act: 6.2667. Min Act: -0.1700
Data Index: 6214026 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5792. Min Range: -6.5792
Max Act: 6.2667. Min Act: -0.1700
Data Index: 5914088 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5792. Min Range: -6.5792
Max Act: 6.2354. Min Act: -0.1700
Data Index: 8155000 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5792. Min Range: -6.5792
Max Act: 6.2667. Min Act: -0.1700
Data Index: 7813989 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5792. Min Range: -6.5792
Max Act: 6.2667. Min Act: -0.1700
Data Index: 4707336 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5792. Min Range: -6.5792
Max Act: 6.2354. Min Act: -0.1700
Data Index: 5894864 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5792. Min Range: -6.5792
Max Act: 6.2354. Min Act: -0.1700
Data Index: 2136514 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5792. Min Range: -6.5792
Max Act: 6.2354. Min Act: -0.1700
Data Index: 1631289 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #19