Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5678 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.0735. Min Range: -3.0735
Max Act: 3.0735. Min Act: -0.1700
Data Index: 4633550 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0735. Min Range: -3.0735
Max Act: 3.0420. Min Act: -0.1700
Data Index: 4633547 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0735. Min Range: -3.0735
Max Act: 2.9629. Min Act: -0.1700
Data Index: 7501218 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0735. Min Range: -3.0735
Max Act: 2.9313. Min Act: -0.1700
Data Index: 3058130 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0735. Min Range: -3.0735
Max Act: 2.9154. Min Act: -0.1700
Data Index: 7447949 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0735. Min Range: -3.0735
Max Act: 2.8996. Min Act: -0.1700
Data Index: 4361719 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0735. Min Range: -3.0735
Max Act: 2.8996. Min Act: -0.1700
Data Index: 3138656 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0735. Min Range: -3.0735
Max Act: 2.9154. Min Act: -0.1700
Data Index: 8702538 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0735. Min Range: -3.0735
Max Act: 2.8837. Min Act: -0.1700
Data Index: 4633546 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0735. Min Range: -3.0735
Max Act: 2.8678. Min Act: -0.1700
Data Index: 3640340 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0735. Min Range: -3.0735
Max Act: 2.8520. Min Act: -0.1700
Data Index: 7695500 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0735. Min Range: -3.0735
Max Act: 2.8042. Min Act: -0.1700
Data Index: 942755 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0735. Min Range: -3.0735
Max Act: 2.8042. Min Act: -0.1700
Data Index: 6113945 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0735. Min Range: -3.0735
Max Act: 2.7883. Min Act: -0.1700
Data Index: 2555310 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0735. Min Range: -3.0735
Max Act: 2.7883. Min Act: -0.1700
Data Index: 8679809 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0735. Min Range: -3.0735
Max Act: 2.7883. Min Act: -0.1700
Data Index: 4540007 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0735. Min Range: -3.0735
Max Act: 2.7724. Min Act: -0.1700
Data Index: 906677 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0735. Min Range: -3.0735
Max Act: 2.7564. Min Act: -0.1700
Data Index: 1770142 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0735. Min Range: -3.0735
Max Act: 2.7724. Min Act: -0.1700
Data Index: 6015484 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0735. Min Range: -3.0735
Max Act: 2.7724. Min Act: -0.1700
Data Index: 95042 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #19