Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3716 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0628. Min Range: -7.0628
Max Act: 7.0628. Min Act: -0.1700
Data Index: 3512471 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0628. Min Range: -7.0628
Max Act: 7.0628. Min Act: -0.1700
Data Index: 1659181 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0628. Min Range: -7.0628
Max Act: 7.0315. Min Act: -0.1700
Data Index: 180313 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0628. Min Range: -7.0628
Max Act: 6.8128. Min Act: -0.1700
Data Index: 6555492 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0628. Min Range: -7.0628
Max Act: 6.6878. Min Act: -0.1700
Data Index: 2100321 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0628. Min Range: -7.0628
Max Act: 6.6565. Min Act: -0.1700
Data Index: 3652113 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0628. Min Range: -7.0628
Max Act: 6.6253. Min Act: -0.1700
Data Index: 1257784 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0628. Min Range: -7.0628
Max Act: 6.6565. Min Act: -0.1700
Data Index: 5820990 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0628. Min Range: -7.0628
Max Act: 6.6253. Min Act: -0.1700
Data Index: 6872964 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0628. Min Range: -7.0628
Max Act: 6.6253. Min Act: -0.1700
Data Index: 2950996 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0628. Min Range: -7.0628
Max Act: 6.5315. Min Act: -0.1700
Data Index: 4786795 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0628. Min Range: -7.0628
Max Act: 6.5003. Min Act: -0.1700
Data Index: 743267 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0628. Min Range: -7.0628
Max Act: 6.4690. Min Act: -0.1700
Data Index: 4036449 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0628. Min Range: -7.0628
Max Act: 6.4690. Min Act: -0.1700
Data Index: 5616081 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0628. Min Range: -7.0628
Max Act: 6.4690. Min Act: -0.1700
Data Index: 3352710 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0628. Min Range: -7.0628
Max Act: 6.4690. Min Act: -0.1700
Data Index: 5222771 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0628. Min Range: -7.0628
Max Act: 6.4378. Min Act: -0.1700
Data Index: 6599779 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0628. Min Range: -7.0628
Max Act: 6.4378. Min Act: -0.1700
Data Index: 5547294 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0628. Min Range: -7.0628
Max Act: 6.4378. Min Act: -0.1700
Data Index: 1584464 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0628. Min Range: -7.0628
Max Act: 6.3753. Min Act: -0.1700
Data Index: 2582982 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #19