Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1254 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0440. Min Range: -6.0440
Max Act: 6.0440. Min Act: -0.1700
Data Index: 2361026 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0440. Min Range: -6.0440
Max Act: 5.6378. Min Act: -0.1700
Data Index: 2737067 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0440. Min Range: -6.0440
Max Act: 5.5753. Min Act: -0.1700
Data Index: 3299216 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0440. Min Range: -6.0440
Max Act: 5.5128. Min Act: -0.1700
Data Index: 931212 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0440. Min Range: -6.0440
Max Act: 5.5128. Min Act: -0.1700
Data Index: 7896066 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0440. Min Range: -6.0440
Max Act: 5.4815. Min Act: -0.1700
Data Index: 1856194 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0440. Min Range: -6.0440
Max Act: 5.4815. Min Act: -0.1700
Data Index: 4756667 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0440. Min Range: -6.0440
Max Act: 5.4503. Min Act: -0.1700
Data Index: 2092777 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0440. Min Range: -6.0440
Max Act: 5.4503. Min Act: -0.1700
Data Index: 113936 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0440. Min Range: -6.0440
Max Act: 5.4503. Min Act: -0.1700
Data Index: 952567 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0440. Min Range: -6.0440
Max Act: 5.4190. Min Act: -0.1700
Data Index: 629094 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0440. Min Range: -6.0440
Max Act: 5.3878. Min Act: -0.1700
Data Index: 2576944 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0440. Min Range: -6.0440
Max Act: 5.3878. Min Act: -0.1700
Data Index: 6214117 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0440. Min Range: -6.0440
Max Act: 5.3878. Min Act: -0.1700
Data Index: 1857210 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0440. Min Range: -6.0440
Max Act: 5.3565. Min Act: -0.1700
Data Index: 6618011 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0440. Min Range: -6.0440
Max Act: 5.3565. Min Act: -0.1700
Data Index: 2381444 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0440. Min Range: -6.0440
Max Act: 5.3565. Min Act: -0.1700
Data Index: 6881025 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0440. Min Range: -6.0440
Max Act: 5.3565. Min Act: -0.1700
Data Index: 6306837 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0440. Min Range: -6.0440
Max Act: 5.3565. Min Act: -0.1700
Data Index: 821138 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0440. Min Range: -6.0440
Max Act: 5.3253. Min Act: -0.1700
Data Index: 4303561 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #19