Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4984 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2901. Min Range: -7.2901
Max Act: 7.2901. Min Act: -0.1700
Data Index: 4414256 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2901. Min Range: -7.2901
Max Act: 6.9776. Min Act: -0.1700
Data Index: 1853546 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2901. Min Range: -7.2901
Max Act: 6.7588. Min Act: -0.1700
Data Index: 8353966 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2901. Min Range: -7.2901
Max Act: 6.7588. Min Act: -0.1700
Data Index: 4266854 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2901. Min Range: -7.2901
Max Act: 6.6651. Min Act: -0.1700
Data Index: 5452116 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2901. Min Range: -7.2901
Max Act: 6.6026. Min Act: -0.1700
Data Index: 1696673 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2901. Min Range: -7.2901
Max Act: 6.6338. Min Act: -0.1700
Data Index: 8045070 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2901. Min Range: -7.2901
Max Act: 6.5713. Min Act: -0.1700
Data Index: 2060899 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2901. Min Range: -7.2901
Max Act: 6.5713. Min Act: -0.1700
Data Index: 2919744 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2901. Min Range: -7.2901
Max Act: 6.5713. Min Act: -0.1700
Data Index: 1482849 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2901. Min Range: -7.2901
Max Act: 6.5713. Min Act: -0.1700
Data Index: 6923922 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2901. Min Range: -7.2901
Max Act: 6.5401. Min Act: -0.1700
Data Index: 6154787 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2901. Min Range: -7.2901
Max Act: 6.5401. Min Act: -0.1700
Data Index: 1164173 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2901. Min Range: -7.2901
Max Act: 6.5401. Min Act: -0.1700
Data Index: 5002551 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2901. Min Range: -7.2901
Max Act: 6.5088. Min Act: -0.1700
Data Index: 2939923 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2901. Min Range: -7.2901
Max Act: 6.5088. Min Act: -0.1700
Data Index: 4847390 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2901. Min Range: -7.2901
Max Act: 6.5088. Min Act: -0.1700
Data Index: 2104692 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2901. Min Range: -7.2901
Max Act: 6.4776. Min Act: -0.1700
Data Index: 7865128 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2901. Min Range: -7.2901
Max Act: 6.4463. Min Act: -0.1700
Data Index: 6223921 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2901. Min Range: -7.2901
Max Act: 6.4151. Min Act: -0.1700
Data Index: 7035268 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #19