Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1849 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0895. Min Range: -7.0895
Max Act: 7.0895. Min Act: -0.1700
Data Index: 8324771 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0895. Min Range: -7.0895
Max Act: 7.0270. Min Act: -0.1700
Data Index: 1101195 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0895. Min Range: -7.0895
Max Act: 6.7770. Min Act: -0.1700
Data Index: 5408885 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0895. Min Range: -7.0895
Max Act: 6.7770. Min Act: -0.1700
Data Index: 566977 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0895. Min Range: -7.0895
Max Act: 6.7770. Min Act: -0.1700
Data Index: 3995197 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0895. Min Range: -7.0895
Max Act: 6.6833. Min Act: -0.1700
Data Index: 4562298 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0895. Min Range: -7.0895
Max Act: 6.6520. Min Act: -0.1700
Data Index: 4031185 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0895. Min Range: -7.0895
Max Act: 6.5895. Min Act: -0.1700
Data Index: 5420041 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0895. Min Range: -7.0895
Max Act: 6.5895. Min Act: -0.1700
Data Index: 160531 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0895. Min Range: -7.0895
Max Act: 6.5583. Min Act: -0.1700
Data Index: 6805000 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0895. Min Range: -7.0895
Max Act: 6.5583. Min Act: -0.1700
Data Index: 238375 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0895. Min Range: -7.0895
Max Act: 6.5270. Min Act: -0.1700
Data Index: 7721486 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0895. Min Range: -7.0895
Max Act: 6.5583. Min Act: -0.1700
Data Index: 3435876 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0895. Min Range: -7.0895
Max Act: 6.5583. Min Act: -0.1700
Data Index: 8373148 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0895. Min Range: -7.0895
Max Act: 6.5583. Min Act: -0.1700
Data Index: 3085899 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0895. Min Range: -7.0895
Max Act: 6.5270. Min Act: -0.1700
Data Index: 684461 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0895. Min Range: -7.0895
Max Act: 6.5270. Min Act: -0.1700
Data Index: 2968729 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0895. Min Range: -7.0895
Max Act: 6.4958. Min Act: -0.1700
Data Index: 875968 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0895. Min Range: -7.0895
Max Act: 6.5270. Min Act: -0.1700
Data Index: 8356953 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0895. Min Range: -7.0895
Max Act: 6.5270. Min Act: -0.1700
Data Index: 3028788 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #19