Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 789 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7547. Min Range: -7.7547
Max Act: 7.7547. Min Act: -0.1700
Data Index: 6533248 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7547. Min Range: -7.7547
Max Act: 7.7235. Min Act: -0.1700
Data Index: 6782694 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7547. Min Range: -7.7547
Max Act: 7.6922. Min Act: -0.1700
Data Index: 6749232 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7547. Min Range: -7.7547
Max Act: 7.6610. Min Act: -0.1700
Data Index: 8591271 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7547. Min Range: -7.7547
Max Act: 7.6610. Min Act: -0.1700
Data Index: 710742 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7547. Min Range: -7.7547
Max Act: 7.6922. Min Act: -0.1700
Data Index: 7714201 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7547. Min Range: -7.7547
Max Act: 7.6610. Min Act: -0.1700
Data Index: 3356990 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7547. Min Range: -7.7547
Max Act: 7.6297. Min Act: -0.1700
Data Index: 5663405 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7547. Min Range: -7.7547
Max Act: 7.5985. Min Act: -0.1700
Data Index: 1024624 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7547. Min Range: -7.7547
Max Act: 7.5672. Min Act: -0.1700
Data Index: 4739496 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7547. Min Range: -7.7547
Max Act: 7.5672. Min Act: -0.1700
Data Index: 8064007 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7547. Min Range: -7.7547
Max Act: 7.5672. Min Act: -0.1700
Data Index: 3530788 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7547. Min Range: -7.7547
Max Act: 7.5360. Min Act: -0.1700
Data Index: 5172512 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7547. Min Range: -7.7547
Max Act: 7.5360. Min Act: -0.1700
Data Index: 6490429 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7547. Min Range: -7.7547
Max Act: 7.5360. Min Act: -0.1700
Data Index: 6242075 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7547. Min Range: -7.7547
Max Act: 7.5047. Min Act: -0.1700
Data Index: 2967786 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7547. Min Range: -7.7547
Max Act: 7.5360. Min Act: -0.1700
Data Index: 2288543 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7547. Min Range: -7.7547
Max Act: 7.5047. Min Act: -0.1700
Data Index: 1664971 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7547. Min Range: -7.7547
Max Act: 7.4735. Min Act: -0.1700
Data Index: 5601730 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7547. Min Range: -7.7547
Max Act: 7.5047. Min Act: -0.1700
Data Index: 430119 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #19