Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4666 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7812. Min Range: -6.7812
Max Act: 6.7812. Min Act: -0.1700
Data Index: 5057798 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7812. Min Range: -6.7812
Max Act: 6.5937. Min Act: -0.1700
Data Index: 7183979 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7812. Min Range: -6.7812
Max Act: 6.5624. Min Act: -0.1700
Data Index: 5397915 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7812. Min Range: -6.7812
Max Act: 6.5624. Min Act: -0.1700
Data Index: 1798728 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7812. Min Range: -6.7812
Max Act: 6.5312. Min Act: -0.1700
Data Index: 4461553 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7812. Min Range: -6.7812
Max Act: 6.4999. Min Act: -0.1700
Data Index: 419006 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7812. Min Range: -6.7812
Max Act: 6.4999. Min Act: -0.1700
Data Index: 5069381 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7812. Min Range: -6.7812
Max Act: 6.4687. Min Act: -0.1700
Data Index: 2104811 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7812. Min Range: -6.7812
Max Act: 6.4687. Min Act: -0.1700
Data Index: 7406502 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7812. Min Range: -6.7812
Max Act: 6.4687. Min Act: -0.1700
Data Index: 852389 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7812. Min Range: -6.7812
Max Act: 6.4687. Min Act: -0.1700
Data Index: 5786176 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7812. Min Range: -6.7812
Max Act: 6.4687. Min Act: -0.1700
Data Index: 5856064 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7812. Min Range: -6.7812
Max Act: 6.4374. Min Act: -0.1700
Data Index: 8646640 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7812. Min Range: -6.7812
Max Act: 6.4374. Min Act: -0.1700
Data Index: 6785689 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7812. Min Range: -6.7812
Max Act: 6.3749. Min Act: -0.1700
Data Index: 7801360 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7812. Min Range: -6.7812
Max Act: 6.4062. Min Act: -0.1700
Data Index: 5113353 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7812. Min Range: -6.7812
Max Act: 6.4062. Min Act: -0.1700
Data Index: 1275230 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7812. Min Range: -6.7812
Max Act: 6.4062. Min Act: -0.1700
Data Index: 5462515 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7812. Min Range: -6.7812
Max Act: 6.3749. Min Act: -0.1700
Data Index: 3821694 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7812. Min Range: -6.7812
Max Act: 6.3749. Min Act: -0.1700
Data Index: 888981 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #19