Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2447 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.1430. Min Range: -8.1430
Max Act: 8.0492. Min Act: -0.1700
Data Index: 5879373 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1430. Min Range: -8.1430
Max Act: 8.1430. Min Act: -0.1700
Data Index: 5597204 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1430. Min Range: -8.1430
Max Act: 7.8305. Min Act: -0.1700
Data Index: 2963670 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1430. Min Range: -8.1430
Max Act: 7.7367. Min Act: -0.1700
Data Index: 7414714 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1430. Min Range: -8.1430
Max Act: 7.7055. Min Act: -0.1700
Data Index: 3290210 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1430. Min Range: -8.1430
Max Act: 7.6430. Min Act: -0.1700
Data Index: 2961748 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1430. Min Range: -8.1430
Max Act: 7.5492. Min Act: -0.1700
Data Index: 2198703 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1430. Min Range: -8.1430
Max Act: 7.4867. Min Act: -0.1700
Data Index: 4960263 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1430. Min Range: -8.1430
Max Act: 7.5492. Min Act: -0.1700
Data Index: 76561 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1430. Min Range: -8.1430
Max Act: 7.5180. Min Act: -0.1700
Data Index: 2474554 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1430. Min Range: -8.1430
Max Act: 7.4867. Min Act: -0.1700
Data Index: 691106 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1430. Min Range: -8.1430
Max Act: 7.4867. Min Act: -0.1700
Data Index: 6036114 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1430. Min Range: -8.1430
Max Act: 7.4242. Min Act: -0.1700
Data Index: 7745131 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1430. Min Range: -8.1430
Max Act: 7.3930. Min Act: -0.1700
Data Index: 7302185 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1430. Min Range: -8.1430
Max Act: 7.3305. Min Act: -0.1700
Data Index: 2432746 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1430. Min Range: -8.1430
Max Act: 7.3305. Min Act: -0.1700
Data Index: 2902768 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1430. Min Range: -8.1430
Max Act: 7.3930. Min Act: -0.1700
Data Index: 829325 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1430. Min Range: -8.1430
Max Act: 7.3617. Min Act: -0.1700
Data Index: 4984374 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1430. Min Range: -8.1430
Max Act: 7.3617. Min Act: -0.1700
Data Index: 7736417 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1430. Min Range: -8.1430
Max Act: 7.3305. Min Act: -0.1700
Data Index: 1329479 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #19