Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3196 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2930. Min Range: -7.2930
Max Act: 7.2930. Min Act: -0.1700
Data Index: 8559942 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2930. Min Range: -7.2930
Max Act: 7.1680. Min Act: -0.1700
Data Index: 5488093 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2930. Min Range: -7.2930
Max Act: 7.1055. Min Act: -0.1700
Data Index: 7443250 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2930. Min Range: -7.2930
Max Act: 7.0117. Min Act: -0.1700
Data Index: 7386987 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2930. Min Range: -7.2930
Max Act: 6.9805. Min Act: -0.1700
Data Index: 5416661 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2930. Min Range: -7.2930
Max Act: 6.8242. Min Act: -0.1700
Data Index: 3152525 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2930. Min Range: -7.2930
Max Act: 6.7930. Min Act: -0.1700
Data Index: 4228217 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2930. Min Range: -7.2930
Max Act: 6.7305. Min Act: -0.1700
Data Index: 5848874 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2930. Min Range: -7.2930
Max Act: 6.7305. Min Act: -0.1700
Data Index: 4893077 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2930. Min Range: -7.2930
Max Act: 6.6992. Min Act: -0.1700
Data Index: 4819122 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2930. Min Range: -7.2930
Max Act: 6.7305. Min Act: -0.1700
Data Index: 4483089 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2930. Min Range: -7.2930
Max Act: 6.5742. Min Act: -0.1700
Data Index: 132067 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2930. Min Range: -7.2930
Max Act: 6.6367. Min Act: -0.1700
Data Index: 2318673 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2930. Min Range: -7.2930
Max Act: 6.5742. Min Act: -0.1700
Data Index: 3661844 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2930. Min Range: -7.2930
Max Act: 6.5430. Min Act: -0.1700
Data Index: 5300715 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2930. Min Range: -7.2930
Max Act: 6.5117. Min Act: -0.1700
Data Index: 2470062 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2930. Min Range: -7.2930
Max Act: 6.4805. Min Act: -0.1700
Data Index: 7725240 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2930. Min Range: -7.2930
Max Act: 6.4805. Min Act: -0.1700
Data Index: 7600359 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2930. Min Range: -7.2930
Max Act: 6.4492. Min Act: -0.1700
Data Index: 5786868 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2930. Min Range: -7.2930
Max Act: 6.4805. Min Act: -0.1700
Data Index: 683150 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #19