Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4670 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.4698. Min Range: -3.4698
Max Act: 3.4698. Min Act: -0.1700
Data Index: 71908 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4698. Min Range: -3.4698
Max Act: 3.4228. Min Act: -0.1700
Data Index: 6732307 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4698. Min Range: -3.4698
Max Act: 3.4071. Min Act: -0.1700
Data Index: 2429621 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4698. Min Range: -3.4698
Max Act: 3.3914. Min Act: -0.1700
Data Index: 7581857 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4698. Min Range: -3.4698
Max Act: 3.3600. Min Act: -0.1700
Data Index: 6797511 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4698. Min Range: -3.4698
Max Act: 3.3757. Min Act: -0.1700
Data Index: 3038322 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4698. Min Range: -3.4698
Max Act: 3.3444. Min Act: -0.1700
Data Index: 6835231 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4698. Min Range: -3.4698
Max Act: 3.3444. Min Act: -0.1700
Data Index: 6179072 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4698. Min Range: -3.4698
Max Act: 3.3444. Min Act: -0.1700
Data Index: 198321 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4698. Min Range: -3.4698
Max Act: 3.3130. Min Act: -0.1700
Data Index: 1305381 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4698. Min Range: -3.4698
Max Act: 3.2973. Min Act: -0.1700
Data Index: 2581886 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4698. Min Range: -3.4698
Max Act: 3.2973. Min Act: -0.1700
Data Index: 1223115 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4698. Min Range: -3.4698
Max Act: 3.2659. Min Act: -0.1700
Data Index: 7310234 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4698. Min Range: -3.4698
Max Act: 3.2659. Min Act: -0.1700
Data Index: 3424920 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4698. Min Range: -3.4698
Max Act: 3.2973. Min Act: -0.1700
Data Index: 6414982 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4698. Min Range: -3.4698
Max Act: 3.2659. Min Act: -0.1700
Data Index: 7490448 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4698. Min Range: -3.4698
Max Act: 3.2659. Min Act: -0.1700
Data Index: 1593016 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4698. Min Range: -3.4698
Max Act: 3.2502. Min Act: -0.1700
Data Index: 1003974 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4698. Min Range: -3.4698
Max Act: 3.2187. Min Act: -0.1700
Data Index: 4932640 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4698. Min Range: -3.4698
Max Act: 3.2344. Min Act: -0.1700
Data Index: 3634879 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #19