Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1792 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.2160. Min Range: -4.2160
Max Act: 4.2160. Min Act: -0.1700
Data Index: 2041370 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2160. Min Range: -4.2160
Max Act: 4.1848. Min Act: -0.1700
Data Index: 3680162 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2160. Min Range: -4.2160
Max Act: 3.9347. Min Act: -0.1700
Data Index: 7522052 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2160. Min Range: -4.2160
Max Act: 3.9347. Min Act: -0.1700
Data Index: 5073895 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2160. Min Range: -4.2160
Max Act: 3.9034. Min Act: -0.1700
Data Index: 8142528 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2160. Min Range: -4.2160
Max Act: 3.9034. Min Act: -0.1700
Data Index: 2376603 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2160. Min Range: -4.2160
Max Act: 3.8722. Min Act: -0.1700
Data Index: 1387561 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2160. Min Range: -4.2160
Max Act: 3.9347. Min Act: -0.1700
Data Index: 7986115 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2160. Min Range: -4.2160
Max Act: 3.9034. Min Act: -0.1700
Data Index: 2544778 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2160. Min Range: -4.2160
Max Act: 3.8722. Min Act: -0.1700
Data Index: 8706883 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2160. Min Range: -4.2160
Max Act: 3.8722. Min Act: -0.1700
Data Index: 4247170 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2160. Min Range: -4.2160
Max Act: 3.9034. Min Act: -0.1700
Data Index: 4258092 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2160. Min Range: -4.2160
Max Act: 3.8722. Min Act: -0.1700
Data Index: 6960043 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2160. Min Range: -4.2160
Max Act: 3.8722. Min Act: -0.1700
Data Index: 819276 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2160. Min Range: -4.2160
Max Act: 3.8722. Min Act: -0.1700
Data Index: 7648232 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2160. Min Range: -4.2160
Max Act: 3.8722. Min Act: -0.1700
Data Index: 4067780 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2160. Min Range: -4.2160
Max Act: 3.8722. Min Act: -0.1700
Data Index: 5487357 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2160. Min Range: -4.2160
Max Act: 3.8409. Min Act: -0.1700
Data Index: 150280 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2160. Min Range: -4.2160
Max Act: 3.8409. Min Act: -0.1700
Data Index: 7922799 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2160. Min Range: -4.2160
Max Act: 3.8409. Min Act: -0.1700
Data Index: 1699412 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #19