Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4768 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9906. Min Range: -4.9906
Max Act: 4.9906. Min Act: -0.1700
Data Index: 4562141 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9906. Min Range: -4.9906
Max Act: 4.9594. Min Act: -0.1700
Data Index: 4296191 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9906. Min Range: -4.9906
Max Act: 4.9594. Min Act: -0.1700
Data Index: 2229166 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9906. Min Range: -4.9906
Max Act: 4.9281. Min Act: -0.1700
Data Index: 7249875 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9906. Min Range: -4.9906
Max Act: 4.8969. Min Act: -0.1699
Data Index: 3111565 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9906. Min Range: -4.9906
Max Act: 4.8656. Min Act: -0.1699
Data Index: 6253111 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9906. Min Range: -4.9906
Max Act: 4.8656. Min Act: -0.1700
Data Index: 3150040 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9906. Min Range: -4.9906
Max Act: 4.8344. Min Act: -0.1700
Data Index: 6975531 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9906. Min Range: -4.9906
Max Act: 4.8344. Min Act: -0.1700
Data Index: 1013642 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9906. Min Range: -4.9906
Max Act: 4.8344. Min Act: -0.1700
Data Index: 8502830 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9906. Min Range: -4.9906
Max Act: 4.8344. Min Act: -0.1700
Data Index: 5279929 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9906. Min Range: -4.9906
Max Act: 4.8344. Min Act: -0.1700
Data Index: 3406170 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9906. Min Range: -4.9906
Max Act: 4.8031. Min Act: -0.1700
Data Index: 1527395 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9906. Min Range: -4.9906
Max Act: 4.8031. Min Act: -0.1700
Data Index: 1513800 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9906. Min Range: -4.9906
Max Act: 4.8031. Min Act: -0.1700
Data Index: 659017 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9906. Min Range: -4.9906
Max Act: 4.7719. Min Act: -0.1700
Data Index: 969067 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9906. Min Range: -4.9906
Max Act: 4.7719. Min Act: -0.1700
Data Index: 4689167 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9906. Min Range: -4.9906
Max Act: 4.7719. Min Act: -0.1700
Data Index: 5009978 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9906. Min Range: -4.9906
Max Act: 4.7719. Min Act: -0.1700
Data Index: 904739 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9906. Min Range: -4.9906
Max Act: 4.7719. Min Act: -0.1700
Data Index: 1023498 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #19