Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2218 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5127. Min Range: -7.5127
Max Act: 7.5127. Min Act: -0.1700
Data Index: 773195 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5127. Min Range: -7.5127
Max Act: 7.4502. Min Act: -0.1700
Data Index: 7581115 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5127. Min Range: -7.5127
Max Act: 7.5127. Min Act: -0.1700
Data Index: 5006386 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5127. Min Range: -7.5127
Max Act: 7.5127. Min Act: -0.1700
Data Index: 1802991 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5127. Min Range: -7.5127
Max Act: 7.4502. Min Act: -0.1700
Data Index: 604590 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5127. Min Range: -7.5127
Max Act: 7.4502. Min Act: -0.1700
Data Index: 7996108 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5127. Min Range: -7.5127
Max Act: 7.4502. Min Act: -0.1700
Data Index: 5663766 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5127. Min Range: -7.5127
Max Act: 7.4502. Min Act: -0.1700
Data Index: 5552392 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5127. Min Range: -7.5127
Max Act: 7.4502. Min Act: -0.1700
Data Index: 730123 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5127. Min Range: -7.5127
Max Act: 7.4502. Min Act: -0.1700
Data Index: 6802829 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5127. Min Range: -7.5127
Max Act: 7.3877. Min Act: -0.1700
Data Index: 4659700 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5127. Min Range: -7.5127
Max Act: 7.3877. Min Act: -0.1700
Data Index: 4502840 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5127. Min Range: -7.5127
Max Act: 7.3877. Min Act: -0.1700
Data Index: 940947 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5127. Min Range: -7.5127
Max Act: 7.3877. Min Act: -0.1700
Data Index: 2156200 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5127. Min Range: -7.5127
Max Act: 7.3877. Min Act: -0.1700
Data Index: 1666196 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5127. Min Range: -7.5127
Max Act: 7.3877. Min Act: -0.1700
Data Index: 4370061 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5127. Min Range: -7.5127
Max Act: 7.3877. Min Act: -0.1700
Data Index: 6767096 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5127. Min Range: -7.5127
Max Act: 7.3877. Min Act: -0.1700
Data Index: 3322929 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5127. Min Range: -7.5127
Max Act: 7.3877. Min Act: -0.1700
Data Index: 1504616 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5127. Min Range: -7.5127
Max Act: 7.3252. Min Act: -0.1700
Data Index: 761002 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #19