Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 968 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9870. Min Range: -6.9870
Max Act: 6.9870. Min Act: -0.1700
Data Index: 6712254 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9870. Min Range: -6.9870
Max Act: 6.9245. Min Act: -0.1700
Data Index: 1255671 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9870. Min Range: -6.9870
Max Act: 6.8620. Min Act: -0.1700
Data Index: 3283591 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9870. Min Range: -6.9870
Max Act: 6.8307. Min Act: -0.1700
Data Index: 1657342 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9870. Min Range: -6.9870
Max Act: 6.7995. Min Act: -0.1700
Data Index: 7050461 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9870. Min Range: -6.9870
Max Act: 6.7682. Min Act: -0.1700
Data Index: 2321252 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9870. Min Range: -6.9870
Max Act: 6.7370. Min Act: -0.1700
Data Index: 2164042 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9870. Min Range: -6.9870
Max Act: 6.7370. Min Act: -0.1700
Data Index: 1451890 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9870. Min Range: -6.9870
Max Act: 6.6432. Min Act: -0.1700
Data Index: 231317 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9870. Min Range: -6.9870
Max Act: 6.6120. Min Act: -0.1700
Data Index: 3183165 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9870. Min Range: -6.9870
Max Act: 6.6120. Min Act: -0.1700
Data Index: 8267270 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9870. Min Range: -6.9870
Max Act: 6.5807. Min Act: -0.1700
Data Index: 5994388 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9870. Min Range: -6.9870
Max Act: 6.5495. Min Act: -0.1700
Data Index: 2242346 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9870. Min Range: -6.9870
Max Act: 6.5495. Min Act: -0.1700
Data Index: 5241396 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9870. Min Range: -6.9870
Max Act: 6.5182. Min Act: -0.1700
Data Index: 509914 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9870. Min Range: -6.9870
Max Act: 6.5182. Min Act: -0.1700
Data Index: 7466607 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9870. Min Range: -6.9870
Max Act: 6.4870. Min Act: -0.1700
Data Index: 1194115 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9870. Min Range: -6.9870
Max Act: 6.4870. Min Act: -0.1700
Data Index: 385622 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9870. Min Range: -6.9870
Max Act: 6.4557. Min Act: -0.1700
Data Index: 5164147 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9870. Min Range: -6.9870
Max Act: 6.4245. Min Act: -0.1700
Data Index: 7005274 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #19