Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 413 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.5092. Min Range: -10.5092
Max Act: 10.5092. Min Act: -0.1700
Data Index: 2101079 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.5092. Min Range: -10.5092
Max Act: 10.3842. Min Act: -0.1700
Data Index: 7936217 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.5092. Min Range: -10.5092
Max Act: 10.3217. Min Act: -0.1700
Data Index: 2303653 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.5092. Min Range: -10.5092
Max Act: 10.3217. Min Act: -0.1700
Data Index: 7210965 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.5092. Min Range: -10.5092
Max Act: 10.3217. Min Act: -0.1700
Data Index: 6265481 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.5092. Min Range: -10.5092
Max Act: 10.1967. Min Act: -0.1700
Data Index: 5722836 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.5092. Min Range: -10.5092
Max Act: 10.1342. Min Act: -0.1700
Data Index: 112113 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.5092. Min Range: -10.5092
Max Act: 9.9467. Min Act: -0.1700
Data Index: 329073 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.5092. Min Range: -10.5092
Max Act: 9.8842. Min Act: -0.1700
Data Index: 2693406 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.5092. Min Range: -10.5092
Max Act: 9.8842. Min Act: -0.1700
Data Index: 3383068 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.5092. Min Range: -10.5092
Max Act: 9.8217. Min Act: -0.1700
Data Index: 3089231 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.5092. Min Range: -10.5092
Max Act: 9.8217. Min Act: -0.1700
Data Index: 6995958 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.5092. Min Range: -10.5092
Max Act: 9.8217. Min Act: -0.1700
Data Index: 138074 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.5092. Min Range: -10.5092
Max Act: 9.7592. Min Act: -0.1700
Data Index: 6486138 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.5092. Min Range: -10.5092
Max Act: 9.7592. Min Act: -0.1700
Data Index: 7260751 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.5092. Min Range: -10.5092
Max Act: 9.7592. Min Act: -0.1700
Data Index: 4718497 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.5092. Min Range: -10.5092
Max Act: 9.7592. Min Act: -0.1700
Data Index: 5803729 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.5092. Min Range: -10.5092
Max Act: 9.7592. Min Act: -0.1700
Data Index: 2112817 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.5092. Min Range: -10.5092
Max Act: 9.7592. Min Act: -0.1700
Data Index: 2749133 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.5092. Min Range: -10.5092
Max Act: 9.7592. Min Act: -0.1700
Data Index: 3281595 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #19