Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3476 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3782. Min Range: -4.3782
Max Act: 4.3782. Min Act: -0.1700
Data Index: 1973202 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3782. Min Range: -4.3782
Max Act: 4.3157. Min Act: -0.1700
Data Index: 8798688 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3782. Min Range: -4.3782
Max Act: 4.2844. Min Act: -0.1700
Data Index: 8581838 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3782. Min Range: -4.3782
Max Act: 4.2532. Min Act: -0.1700
Data Index: 62004 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3782. Min Range: -4.3782
Max Act: 4.2532. Min Act: -0.1700
Data Index: 4029189 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3782. Min Range: -4.3782
Max Act: 4.2219. Min Act: -0.1700
Data Index: 8709451 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3782. Min Range: -4.3782
Max Act: 4.2532. Min Act: -0.1700
Data Index: 1641082 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3782. Min Range: -4.3782
Max Act: 4.2219. Min Act: -0.1700
Data Index: 2274728 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3782. Min Range: -4.3782
Max Act: 4.2219. Min Act: -0.1700
Data Index: 6054883 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3782. Min Range: -4.3782
Max Act: 4.1906. Min Act: -0.1700
Data Index: 8772166 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3782. Min Range: -4.3782
Max Act: 4.1906. Min Act: -0.1700
Data Index: 4644495 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3782. Min Range: -4.3782
Max Act: 4.1594. Min Act: -0.1700
Data Index: 1199120 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3782. Min Range: -4.3782
Max Act: 4.1594. Min Act: -0.1700
Data Index: 4975818 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3782. Min Range: -4.3782
Max Act: 4.1281. Min Act: -0.1700
Data Index: 4095043 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3782. Min Range: -4.3782
Max Act: 4.1594. Min Act: -0.1700
Data Index: 2709986 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3782. Min Range: -4.3782
Max Act: 4.1594. Min Act: -0.1700
Data Index: 2776009 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3782. Min Range: -4.3782
Max Act: 4.1281. Min Act: -0.1700
Data Index: 7282772 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3782. Min Range: -4.3782
Max Act: 4.1281. Min Act: -0.1700
Data Index: 4091606 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3782. Min Range: -4.3782
Max Act: 4.1281. Min Act: -0.1699
Data Index: 6775468 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3782. Min Range: -4.3782
Max Act: 4.1281. Min Act: -0.1700
Data Index: 7318869 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #19