Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2522 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0981. Min Range: -8.0981
Max Act: 8.0981. Min Act: -0.1700
Data Index: 7053362 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0981. Min Range: -8.0981
Max Act: 7.9106. Min Act: -0.1700
Data Index: 65656 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0981. Min Range: -8.0981
Max Act: 7.9106. Min Act: -0.1700
Data Index: 3787693 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0981. Min Range: -8.0981
Max Act: 7.7856. Min Act: -0.1700
Data Index: 8470561 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0981. Min Range: -8.0981
Max Act: 7.7856. Min Act: -0.1700
Data Index: 2339054 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0981. Min Range: -8.0981
Max Act: 7.7856. Min Act: -0.1700
Data Index: 3273585 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0981. Min Range: -8.0981
Max Act: 7.7856. Min Act: -0.1700
Data Index: 1750987 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0981. Min Range: -8.0981
Max Act: 7.7231. Min Act: -0.1700
Data Index: 6073546 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0981. Min Range: -8.0981
Max Act: 7.6606. Min Act: -0.1700
Data Index: 4415744 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0981. Min Range: -8.0981
Max Act: 7.6606. Min Act: -0.1700
Data Index: 7695986 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0981. Min Range: -8.0981
Max Act: 7.6606. Min Act: -0.1700
Data Index: 8477550 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0981. Min Range: -8.0981
Max Act: 7.6606. Min Act: -0.1700
Data Index: 2575419 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0981. Min Range: -8.0981
Max Act: 7.5981. Min Act: -0.1700
Data Index: 7199784 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0981. Min Range: -8.0981
Max Act: 7.5981. Min Act: -0.1700
Data Index: 631110 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0981. Min Range: -8.0981
Max Act: 7.5356. Min Act: -0.1700
Data Index: 6164843 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0981. Min Range: -8.0981
Max Act: 7.5356. Min Act: -0.1700
Data Index: 8620080 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0981. Min Range: -8.0981
Max Act: 7.5356. Min Act: -0.1700
Data Index: 2965606 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0981. Min Range: -8.0981
Max Act: 7.5356. Min Act: -0.1700
Data Index: 6748597 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0981. Min Range: -8.0981
Max Act: 7.4106. Min Act: -0.1700
Data Index: 409475 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0981. Min Range: -8.0981
Max Act: 7.4731. Min Act: -0.1700
Data Index: 2884699 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #19