Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3877 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1874. Min Range: -7.1874
Max Act: 7.1874. Min Act: -0.1700
Data Index: 468003 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1874. Min Range: -7.1874
Max Act: 6.9999. Min Act: -0.1700
Data Index: 4661110 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1874. Min Range: -7.1874
Max Act: 6.9062. Min Act: -0.1700
Data Index: 792074 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1874. Min Range: -7.1874
Max Act: 6.8437. Min Act: -0.1700
Data Index: 1981457 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1874. Min Range: -7.1874
Max Act: 6.8437. Min Act: -0.1700
Data Index: 2412564 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1874. Min Range: -7.1874
Max Act: 6.8124. Min Act: -0.1700
Data Index: 6395162 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1874. Min Range: -7.1874
Max Act: 6.7812. Min Act: -0.1700
Data Index: 2974994 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1874. Min Range: -7.1874
Max Act: 6.7499. Min Act: -0.1700
Data Index: 2791909 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1874. Min Range: -7.1874
Max Act: 6.7499. Min Act: -0.1700
Data Index: 4462612 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1874. Min Range: -7.1874
Max Act: 6.7187. Min Act: -0.1700
Data Index: 7349736 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1874. Min Range: -7.1874
Max Act: 6.7187. Min Act: -0.1700
Data Index: 1707581 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1874. Min Range: -7.1874
Max Act: 6.6562. Min Act: -0.1700
Data Index: 1589980 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1874. Min Range: -7.1874
Max Act: 6.6874. Min Act: -0.1700
Data Index: 1431206 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1874. Min Range: -7.1874
Max Act: 6.6874. Min Act: -0.1700
Data Index: 753836 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1874. Min Range: -7.1874
Max Act: 6.6249. Min Act: -0.1700
Data Index: 4963193 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1874. Min Range: -7.1874
Max Act: 6.6249. Min Act: -0.1700
Data Index: 6598812 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1874. Min Range: -7.1874
Max Act: 6.5624. Min Act: -0.1700
Data Index: 1175173 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1874. Min Range: -7.1874
Max Act: 6.5312. Min Act: -0.1700
Data Index: 5792091 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1874. Min Range: -7.1874
Max Act: 6.5312. Min Act: -0.1700
Data Index: 1433559 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1874. Min Range: -7.1874
Max Act: 6.5312. Min Act: -0.1700
Data Index: 3209194 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #19