Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3831 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0088. Min Range: -7.0088
Max Act: 7.0088. Min Act: -0.1700
Data Index: 1195809 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0088. Min Range: -7.0088
Max Act: 6.9150. Min Act: -0.1700
Data Index: 196872 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0088. Min Range: -7.0088
Max Act: 6.9150. Min Act: -0.1700
Data Index: 1986718 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0088. Min Range: -7.0088
Max Act: 6.9150. Min Act: -0.1700
Data Index: 5666504 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0088. Min Range: -7.0088
Max Act: 6.8838. Min Act: -0.1700
Data Index: 7879620 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0088. Min Range: -7.0088
Max Act: 6.8525. Min Act: -0.1700
Data Index: 6518688 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0088. Min Range: -7.0088
Max Act: 6.8213. Min Act: -0.1700
Data Index: 3816940 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0088. Min Range: -7.0088
Max Act: 6.8213. Min Act: -0.1700
Data Index: 2678860 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0088. Min Range: -7.0088
Max Act: 6.7900. Min Act: -0.1700
Data Index: 1466709 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0088. Min Range: -7.0088
Max Act: 6.7588. Min Act: -0.1700
Data Index: 6080371 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0088. Min Range: -7.0088
Max Act: 6.7275. Min Act: -0.1700
Data Index: 8267273 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0088. Min Range: -7.0088
Max Act: 6.7275. Min Act: -0.1700
Data Index: 8320314 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0088. Min Range: -7.0088
Max Act: 6.7588. Min Act: -0.1700
Data Index: 711630 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0088. Min Range: -7.0088
Max Act: 6.6650. Min Act: -0.1700
Data Index: 3323831 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0088. Min Range: -7.0088
Max Act: 6.7275. Min Act: -0.1700
Data Index: 4081295 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0088. Min Range: -7.0088
Max Act: 6.6338. Min Act: -0.1700
Data Index: 753107 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0088. Min Range: -7.0088
Max Act: 6.5713. Min Act: -0.1700
Data Index: 7248983 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0088. Min Range: -7.0088
Max Act: 6.5713. Min Act: -0.1700
Data Index: 5619366 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0088. Min Range: -7.0088
Max Act: 6.6025. Min Act: -0.1700
Data Index: 5827332 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0088. Min Range: -7.0088
Max Act: 6.6025. Min Act: -0.1700
Data Index: 4611009 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #19