Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3629 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6788. Min Range: -4.6788
Max Act: 4.6788. Min Act: -0.1700
Data Index: 7949093 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6788. Min Range: -4.6788
Max Act: 4.6163. Min Act: -0.1700
Data Index: 2635666 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6788. Min Range: -4.6788
Max Act: 4.6163. Min Act: -0.1700
Data Index: 1450091 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6788. Min Range: -4.6788
Max Act: 4.5538. Min Act: -0.1700
Data Index: 6764154 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6788. Min Range: -4.6788
Max Act: 4.4913. Min Act: -0.1700
Data Index: 6702455 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6788. Min Range: -4.6788
Max Act: 4.4913. Min Act: -0.1700
Data Index: 4446638 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6788. Min Range: -4.6788
Max Act: 4.4913. Min Act: -0.1700
Data Index: 736200 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6788. Min Range: -4.6788
Max Act: 4.4600. Min Act: -0.1700
Data Index: 3211310 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6788. Min Range: -4.6788
Max Act: 4.4288. Min Act: -0.1700
Data Index: 1048464 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6788. Min Range: -4.6788
Max Act: 4.4600. Min Act: -0.1700
Data Index: 7815035 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6788. Min Range: -4.6788
Max Act: 4.3975. Min Act: -0.1700
Data Index: 5396052 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6788. Min Range: -4.6788
Max Act: 4.3975. Min Act: -0.1700
Data Index: 6511098 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6788. Min Range: -4.6788
Max Act: 4.3975. Min Act: -0.1700
Data Index: 4235010 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6788. Min Range: -4.6788
Max Act: 4.3662. Min Act: -0.1700
Data Index: 2388977 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6788. Min Range: -4.6788
Max Act: 4.3350. Min Act: -0.1700
Data Index: 7993712 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6788. Min Range: -4.6788
Max Act: 4.3350. Min Act: -0.1700
Data Index: 5724080 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6788. Min Range: -4.6788
Max Act: 4.3350. Min Act: -0.1700
Data Index: 6058913 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6788. Min Range: -4.6788
Max Act: 4.3350. Min Act: -0.1700
Data Index: 6270122 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6788. Min Range: -4.6788
Max Act: 4.3350. Min Act: -0.1700
Data Index: 4220847 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6788. Min Range: -4.6788
Max Act: 4.3350. Min Act: -0.1700
Data Index: 6308121 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #19