Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 175 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.1777. Min Range: -7.1777
Max Act: 7.1777. Min Act: -0.1700
Data Index: 4070759 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1777. Min Range: -7.1777
Max Act: 6.7402. Min Act: -0.1700
Data Index: 3540992 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1777. Min Range: -7.1777
Max Act: 6.7089. Min Act: -0.1700
Data Index: 8671226 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1777. Min Range: -7.1777
Max Act: 6.7089. Min Act: -0.1700
Data Index: 3258048 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1777. Min Range: -7.1777
Max Act: 6.7089. Min Act: -0.1700
Data Index: 6677113 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1777. Min Range: -7.1777
Max Act: 6.6464. Min Act: -0.1700
Data Index: 985772 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1777. Min Range: -7.1777
Max Act: 6.6464. Min Act: -0.1700
Data Index: 895824 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1777. Min Range: -7.1777
Max Act: 6.6464. Min Act: -0.1700
Data Index: 3653246 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1777. Min Range: -7.1777
Max Act: 6.6152. Min Act: -0.1700
Data Index: 8130365 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1777. Min Range: -7.1777
Max Act: 6.6152. Min Act: -0.1700
Data Index: 7208022 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1777. Min Range: -7.1777
Max Act: 6.5839. Min Act: -0.1700
Data Index: 7040622 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1777. Min Range: -7.1777
Max Act: 6.5839. Min Act: -0.1700
Data Index: 4201043 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1777. Min Range: -7.1777
Max Act: 6.5214. Min Act: -0.1700
Data Index: 7854025 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1777. Min Range: -7.1777
Max Act: 6.5214. Min Act: -0.1700
Data Index: 4650867 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1777. Min Range: -7.1777
Max Act: 6.5839. Min Act: -0.1700
Data Index: 6951435 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1777. Min Range: -7.1777
Max Act: 6.5527. Min Act: -0.1700
Data Index: 390651 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1777. Min Range: -7.1777
Max Act: 6.5214. Min Act: -0.1700
Data Index: 729350 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1777. Min Range: -7.1777
Max Act: 6.4902. Min Act: -0.1700
Data Index: 6867396 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1777. Min Range: -7.1777
Max Act: 6.4902. Min Act: -0.1700
Data Index: 4046552 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1777. Min Range: -7.1777
Max Act: 6.4589. Min Act: -0.1700
Data Index: 2369649 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #19