Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3636 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7912. Min Range: -6.7912
Max Act: 6.7912. Min Act: -0.1700
Data Index: 76228 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7912. Min Range: -6.7912
Max Act: 6.6349. Min Act: -0.1700
Data Index: 3015430 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7912. Min Range: -6.7912
Max Act: 6.6037. Min Act: -0.1700
Data Index: 6693742 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7912. Min Range: -6.7912
Max Act: 6.5412. Min Act: -0.1700
Data Index: 8403410 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7912. Min Range: -6.7912
Max Act: 6.4162. Min Act: -0.1700
Data Index: 6241672 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7912. Min Range: -6.7912
Max Act: 6.4162. Min Act: -0.1700
Data Index: 4389818 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7912. Min Range: -6.7912
Max Act: 6.3849. Min Act: -0.1700
Data Index: 7848007 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7912. Min Range: -6.7912
Max Act: 6.3537. Min Act: -0.1700
Data Index: 583842 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7912. Min Range: -6.7912
Max Act: 6.3537. Min Act: -0.1700
Data Index: 7906202 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7912. Min Range: -6.7912
Max Act: 6.3537. Min Act: -0.1700
Data Index: 2395146 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7912. Min Range: -6.7912
Max Act: 6.2599. Min Act: -0.1700
Data Index: 3875013 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7912. Min Range: -6.7912
Max Act: 6.2287. Min Act: -0.1700
Data Index: 1425692 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7912. Min Range: -6.7912
Max Act: 6.2287. Min Act: -0.1700
Data Index: 2319470 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7912. Min Range: -6.7912
Max Act: 6.1974. Min Act: -0.1700
Data Index: 3718465 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7912. Min Range: -6.7912
Max Act: 6.1974. Min Act: -0.1700
Data Index: 4266355 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7912. Min Range: -6.7912
Max Act: 6.1662. Min Act: -0.1700
Data Index: 882467 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7912. Min Range: -6.7912
Max Act: 6.1349. Min Act: -0.1700
Data Index: 1251993 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7912. Min Range: -6.7912
Max Act: 6.1349. Min Act: -0.1700
Data Index: 966926 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7912. Min Range: -6.7912
Max Act: 6.1037. Min Act: -0.1700
Data Index: 3243855 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7912. Min Range: -6.7912
Max Act: 6.1349. Min Act: -0.1700
Data Index: 3519963 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #19