Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 843 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3458. Min Range: -5.3458
Max Act: 5.3458. Min Act: -0.1700
Data Index: 6850113 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3458. Min Range: -5.3458
Max Act: 5.2521. Min Act: -0.1693
Data Index: 606223 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3458. Min Range: -5.3458
Max Act: 5.2521. Min Act: -0.1700
Data Index: 1759613 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3458. Min Range: -5.3458
Max Act: 5.2833. Min Act: -0.1700
Data Index: 7559190 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3458. Min Range: -5.3458
Max Act: 5.2208. Min Act: -0.1700
Data Index: 4428542 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3458. Min Range: -5.3458
Max Act: 5.2208. Min Act: -0.1700
Data Index: 8166296 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3458. Min Range: -5.3458
Max Act: 5.1896. Min Act: -0.1700
Data Index: 8415366 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3458. Min Range: -5.3458
Max Act: 5.1896. Min Act: -0.1700
Data Index: 4193694 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3458. Min Range: -5.3458
Max Act: 5.0958. Min Act: -0.1700
Data Index: 887701 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3458. Min Range: -5.3458
Max Act: 5.0958. Min Act: -0.1700
Data Index: 832954 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3458. Min Range: -5.3458
Max Act: 5.0333. Min Act: -0.1700
Data Index: 7215741 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3458. Min Range: -5.3458
Max Act: 5.0333. Min Act: -0.1700
Data Index: 6813602 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3458. Min Range: -5.3458
Max Act: 5.0333. Min Act: -0.1700
Data Index: 7907253 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3458. Min Range: -5.3458
Max Act: 5.0021. Min Act: -0.1700
Data Index: 526828 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3458. Min Range: -5.3458
Max Act: 5.0333. Min Act: -0.1700
Data Index: 2227028 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3458. Min Range: -5.3458
Max Act: 5.0021. Min Act: -0.1700
Data Index: 454752 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3458. Min Range: -5.3458
Max Act: 5.0021. Min Act: -0.1700
Data Index: 5576847 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3458. Min Range: -5.3458
Max Act: 5.0021. Min Act: -0.1700
Data Index: 7999442 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3458. Min Range: -5.3458
Max Act: 5.0021. Min Act: -0.1700
Data Index: 3791562 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3458. Min Range: -5.3458
Max Act: 5.0021. Min Act: -0.1700
Data Index: 1591050 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #19