Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1772 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1753. Min Range: -7.1753
Max Act: 7.1753. Min Act: -0.1700
Data Index: 6829316 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1753. Min Range: -7.1753
Max Act: 7.0503. Min Act: -0.1700
Data Index: 5108644 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1753. Min Range: -7.1753
Max Act: 6.9878. Min Act: -0.1700
Data Index: 1966075 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1753. Min Range: -7.1753
Max Act: 6.9878. Min Act: -0.1700
Data Index: 8422496 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1753. Min Range: -7.1753
Max Act: 6.9878. Min Act: -0.1700
Data Index: 2645105 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1753. Min Range: -7.1753
Max Act: 6.9253. Min Act: -0.1700
Data Index: 4545747 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1753. Min Range: -7.1753
Max Act: 6.9253. Min Act: -0.1700
Data Index: 1664594 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1753. Min Range: -7.1753
Max Act: 6.8941. Min Act: -0.1700
Data Index: 149338 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1753. Min Range: -7.1753
Max Act: 6.8628. Min Act: -0.1700
Data Index: 3995204 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1753. Min Range: -7.1753
Max Act: 6.8628. Min Act: -0.1700
Data Index: 485318 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1753. Min Range: -7.1753
Max Act: 6.8316. Min Act: -0.1700
Data Index: 994923 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1753. Min Range: -7.1753
Max Act: 6.8316. Min Act: -0.1700
Data Index: 1619578 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1753. Min Range: -7.1753
Max Act: 6.8316. Min Act: -0.1700
Data Index: 1543219 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1753. Min Range: -7.1753
Max Act: 6.8316. Min Act: -0.1700
Data Index: 5271894 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1753. Min Range: -7.1753
Max Act: 6.8003. Min Act: -0.1700
Data Index: 6384058 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1753. Min Range: -7.1753
Max Act: 6.7691. Min Act: -0.1700
Data Index: 6015387 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1753. Min Range: -7.1753
Max Act: 6.7378. Min Act: -0.1700
Data Index: 5779151 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1753. Min Range: -7.1753
Max Act: 6.8003. Min Act: -0.1700
Data Index: 6800983 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1753. Min Range: -7.1753
Max Act: 6.7066. Min Act: -0.1700
Data Index: 6991133 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1753. Min Range: -7.1753
Max Act: 6.7066. Min Act: -0.1700
Data Index: 6165632 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #19