Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1415 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.3823. Min Range: -4.3823
Max Act: 4.3823. Min Act: -0.1700
Data Index: 945088 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3823. Min Range: -4.3823
Max Act: 4.3823. Min Act: -0.1700
Data Index: 2995326 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3823. Min Range: -4.3823
Max Act: 4.3511. Min Act: -0.1700
Data Index: 2756202 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3823. Min Range: -4.3823
Max Act: 4.3198. Min Act: -0.1700
Data Index: 7383423 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3823. Min Range: -4.3823
Max Act: 4.2573. Min Act: -0.1700
Data Index: 3117133 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3823. Min Range: -4.3823
Max Act: 4.1948. Min Act: -0.1700
Data Index: 8812034 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3823. Min Range: -4.3823
Max Act: 4.1948. Min Act: -0.1700
Data Index: 5727503 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3823. Min Range: -4.3823
Max Act: 4.1636. Min Act: -0.1700
Data Index: 6285415 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3823. Min Range: -4.3823
Max Act: 4.1636. Min Act: -0.1700
Data Index: 1209841 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3823. Min Range: -4.3823
Max Act: 4.1011. Min Act: -0.1700
Data Index: 8174577 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3823. Min Range: -4.3823
Max Act: 4.1323. Min Act: -0.1700
Data Index: 4318103 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3823. Min Range: -4.3823
Max Act: 4.1323. Min Act: -0.1700
Data Index: 4065213 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3823. Min Range: -4.3823
Max Act: 4.0385. Min Act: -0.1700
Data Index: 5070760 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3823. Min Range: -4.3823
Max Act: 4.1011. Min Act: -0.1700
Data Index: 2930163 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3823. Min Range: -4.3823
Max Act: 4.0698. Min Act: -0.1700
Data Index: 1799759 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3823. Min Range: -4.3823
Max Act: 4.0698. Min Act: -0.1700
Data Index: 3461357 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3823. Min Range: -4.3823
Max Act: 4.0698. Min Act: -0.1700
Data Index: 5697527 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3823. Min Range: -4.3823
Max Act: 4.1011. Min Act: -0.1700
Data Index: 7968954 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3823. Min Range: -4.3823
Max Act: 4.0698. Min Act: -0.1700
Data Index: 774710 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3823. Min Range: -4.3823
Max Act: 4.0385. Min Act: -0.1700
Data Index: 6061741 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #19