Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2659 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5714. Min Range: -4.5714
Max Act: 4.5714. Min Act: -0.1700
Data Index: 2387116 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5714. Min Range: -4.5714
Max Act: 4.5401. Min Act: -0.1700
Data Index: 4469200 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5714. Min Range: -4.5714
Max Act: 4.5089. Min Act: -0.1700
Data Index: 5314559 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5714. Min Range: -4.5714
Max Act: 4.5089. Min Act: -0.1700
Data Index: 4099993 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5714. Min Range: -4.5714
Max Act: 4.5089. Min Act: -0.1700
Data Index: 2710581 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5714. Min Range: -4.5714
Max Act: 4.5089. Min Act: -0.1700
Data Index: 2475800 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5714. Min Range: -4.5714
Max Act: 4.5089. Min Act: -0.1700
Data Index: 3400140 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5714. Min Range: -4.5714
Max Act: 4.4776. Min Act: -0.1700
Data Index: 8817543 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5714. Min Range: -4.5714
Max Act: 4.4776. Min Act: -0.1700
Data Index: 2276765 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5714. Min Range: -4.5714
Max Act: 4.4464. Min Act: -0.1700
Data Index: 4580308 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5714. Min Range: -4.5714
Max Act: 4.4464. Min Act: -0.1700
Data Index: 2155027 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5714. Min Range: -4.5714
Max Act: 4.4464. Min Act: -0.1700
Data Index: 6490327 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5714. Min Range: -4.5714
Max Act: 4.4776. Min Act: -0.1700
Data Index: 7031741 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5714. Min Range: -4.5714
Max Act: 4.4776. Min Act: -0.1700
Data Index: 1235604 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5714. Min Range: -4.5714
Max Act: 4.4151. Min Act: -0.1700
Data Index: 1363828 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5714. Min Range: -4.5714
Max Act: 4.4151. Min Act: -0.1700
Data Index: 4546630 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5714. Min Range: -4.5714
Max Act: 4.4151. Min Act: -0.1700
Data Index: 4787 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5714. Min Range: -4.5714
Max Act: 4.4151. Min Act: -0.1700
Data Index: 4697019 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5714. Min Range: -4.5714
Max Act: 4.3839. Min Act: -0.1700
Data Index: 8759763 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5714. Min Range: -4.5714
Max Act: 4.3839. Min Act: -0.1700
Data Index: 2250910 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #19