Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5657 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8083. Min Range: -6.8083
Max Act: 6.8083. Min Act: -0.1700
Data Index: 8748736 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8083. Min Range: -6.8083
Max Act: 6.5896. Min Act: -0.1700
Data Index: 4436345 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8083. Min Range: -6.8083
Max Act: 6.4646. Min Act: -0.1700
Data Index: 5112176 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8083. Min Range: -6.8083
Max Act: 6.4646. Min Act: -0.1700
Data Index: 2750160 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8083. Min Range: -6.8083
Max Act: 6.4021. Min Act: -0.1700
Data Index: 2822453 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8083. Min Range: -6.8083
Max Act: 6.3708. Min Act: -0.1700
Data Index: 390655 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8083. Min Range: -6.8083
Max Act: 6.3708. Min Act: -0.1700
Data Index: 4335560 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8083. Min Range: -6.8083
Max Act: 6.3708. Min Act: -0.1700
Data Index: 4074250 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8083. Min Range: -6.8083
Max Act: 6.3396. Min Act: -0.1700
Data Index: 8800553 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8083. Min Range: -6.8083
Max Act: 6.3396. Min Act: -0.1700
Data Index: 7318889 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8083. Min Range: -6.8083
Max Act: 6.3396. Min Act: -0.1700
Data Index: 5588406 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8083. Min Range: -6.8083
Max Act: 6.2771. Min Act: -0.1700
Data Index: 5874201 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8083. Min Range: -6.8083
Max Act: 6.3396. Min Act: -0.1700
Data Index: 651419 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8083. Min Range: -6.8083
Max Act: 6.3083. Min Act: -0.1700
Data Index: 2861932 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8083. Min Range: -6.8083
Max Act: 6.3083. Min Act: -0.1700
Data Index: 2485355 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8083. Min Range: -6.8083
Max Act: 6.3083. Min Act: -0.1700
Data Index: 5331117 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8083. Min Range: -6.8083
Max Act: 6.3083. Min Act: -0.1700
Data Index: 3012400 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8083. Min Range: -6.8083
Max Act: 6.3083. Min Act: -0.1700
Data Index: 7778983 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8083. Min Range: -6.8083
Max Act: 6.3083. Min Act: -0.1700
Data Index: 653559 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8083. Min Range: -6.8083
Max Act: 6.3083. Min Act: -0.1700
Data Index: 5015469 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #19