Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2984 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3105. Min Range: -6.3105
Max Act: 6.3105. Min Act: -0.1700
Data Index: 38689 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3105. Min Range: -6.3105
Max Act: 6.2793. Min Act: -0.1700
Data Index: 8386407 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3105. Min Range: -6.3105
Max Act: 6.2793. Min Act: -0.1700
Data Index: 7852314 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3105. Min Range: -6.3105
Max Act: 6.2793. Min Act: -0.1700
Data Index: 5315549 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3105. Min Range: -6.3105
Max Act: 6.2480. Min Act: -0.1700
Data Index: 4980424 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3105. Min Range: -6.3105
Max Act: 6.2480. Min Act: -0.1700
Data Index: 3971887 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3105. Min Range: -6.3105
Max Act: 6.2793. Min Act: -0.1700
Data Index: 160526 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3105. Min Range: -6.3105
Max Act: 6.1855. Min Act: -0.1700
Data Index: 6315235 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3105. Min Range: -6.3105
Max Act: 6.1230. Min Act: -0.1700
Data Index: 7023800 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3105. Min Range: -6.3105
Max Act: 6.0918. Min Act: -0.1700
Data Index: 3660165 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3105. Min Range: -6.3105
Max Act: 6.0293. Min Act: -0.1700
Data Index: 801942 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3105. Min Range: -6.3105
Max Act: 6.0293. Min Act: -0.1700
Data Index: 8116434 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3105. Min Range: -6.3105
Max Act: 5.9980. Min Act: -0.1700
Data Index: 5341896 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3105. Min Range: -6.3105
Max Act: 5.9980. Min Act: -0.1700
Data Index: 2600068 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3105. Min Range: -6.3105
Max Act: 5.9980. Min Act: -0.1700
Data Index: 350049 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3105. Min Range: -6.3105
Max Act: 5.9668. Min Act: -0.1700
Data Index: 4268552 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3105. Min Range: -6.3105
Max Act: 5.9668. Min Act: -0.1700
Data Index: 5132039 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3105. Min Range: -6.3105
Max Act: 5.9980. Min Act: -0.1700
Data Index: 981939 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3105. Min Range: -6.3105
Max Act: 5.9043. Min Act: -0.1700
Data Index: 397851 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3105. Min Range: -6.3105
Max Act: 5.9355. Min Act: -0.1700
Data Index: 7247147 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #19