Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2939 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7861. Min Range: -6.7861
Max Act: 6.7861. Min Act: -0.1700
Data Index: 2156787 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7861. Min Range: -6.7861
Max Act: 6.5361. Min Act: -0.1700
Data Index: 7741526 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7861. Min Range: -6.7861
Max Act: 6.3173. Min Act: -0.1700
Data Index: 1579245 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7861. Min Range: -6.7861
Max Act: 6.2861. Min Act: -0.1700
Data Index: 6182665 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7861. Min Range: -6.7861
Max Act: 6.2548. Min Act: -0.1700
Data Index: 2320401 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7861. Min Range: -6.7861
Max Act: 6.2548. Min Act: -0.1700
Data Index: 2831963 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7861. Min Range: -6.7861
Max Act: 6.1923. Min Act: -0.1700
Data Index: 8578952 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7861. Min Range: -6.7861
Max Act: 6.1298. Min Act: -0.1700
Data Index: 6783756 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7861. Min Range: -6.7861
Max Act: 6.1298. Min Act: -0.1700
Data Index: 4568969 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7861. Min Range: -6.7861
Max Act: 6.0986. Min Act: -0.1700
Data Index: 711744 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7861. Min Range: -6.7861
Max Act: 6.0986. Min Act: -0.1700
Data Index: 662323 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7861. Min Range: -6.7861
Max Act: 6.0673. Min Act: -0.1700
Data Index: 2340460 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7861. Min Range: -6.7861
Max Act: 6.0673. Min Act: -0.1700
Data Index: 5968095 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7861. Min Range: -6.7861
Max Act: 6.0361. Min Act: -0.1700
Data Index: 3122976 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7861. Min Range: -6.7861
Max Act: 6.0361. Min Act: -0.1700
Data Index: 2895080 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7861. Min Range: -6.7861
Max Act: 6.0048. Min Act: -0.1700
Data Index: 1205797 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7861. Min Range: -6.7861
Max Act: 6.0048. Min Act: -0.1700
Data Index: 4020042 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7861. Min Range: -6.7861
Max Act: 5.9111. Min Act: -0.1700
Data Index: 3717375 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7861. Min Range: -6.7861
Max Act: 5.9111. Min Act: -0.1700
Data Index: 3771610 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7861. Min Range: -6.7861
Max Act: 5.9111. Min Act: -0.1700
Data Index: 1342841 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #19