Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3534 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.2340. Min Range: -3.2340
Max Act: 3.2340. Min Act: -0.1700
Data Index: 8437810 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2340. Min Range: -3.2340
Max Act: 3.2183. Min Act: -0.1700
Data Index: 7714333 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2340. Min Range: -3.2340
Max Act: 3.1239. Min Act: -0.1700
Data Index: 7048554 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2340. Min Range: -3.2340
Max Act: 3.1081. Min Act: -0.1700
Data Index: 496949 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2340. Min Range: -3.2340
Max Act: 3.0608. Min Act: -0.1700
Data Index: 122147 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2340. Min Range: -3.2340
Max Act: 3.0608. Min Act: -0.1700
Data Index: 997721 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2340. Min Range: -3.2340
Max Act: 3.0766. Min Act: -0.1700
Data Index: 7970601 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2340. Min Range: -3.2340
Max Act: 3.0450. Min Act: -0.1700
Data Index: 7145802 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2340. Min Range: -3.2340
Max Act: 3.0293. Min Act: -0.1700
Data Index: 4353922 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2340. Min Range: -3.2340
Max Act: 3.0293. Min Act: -0.1700
Data Index: 2840189 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2340. Min Range: -3.2340
Max Act: 3.0135. Min Act: -0.1700
Data Index: 5390294 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2340. Min Range: -3.2340
Max Act: 2.9977. Min Act: -0.1700
Data Index: 4623039 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2340. Min Range: -3.2340
Max Act: 2.9977. Min Act: -0.1700
Data Index: 6267342 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2340. Min Range: -3.2340
Max Act: 2.9977. Min Act: -0.1700
Data Index: 2934317 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2340. Min Range: -3.2340
Max Act: 2.9819. Min Act: -0.1700
Data Index: 2036373 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2340. Min Range: -3.2340
Max Act: 2.9819. Min Act: -0.1700
Data Index: 2758021 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2340. Min Range: -3.2340
Max Act: 2.9977. Min Act: -0.1700
Data Index: 7838976 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2340. Min Range: -3.2340
Max Act: 2.9660. Min Act: -0.1700
Data Index: 1849438 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2340. Min Range: -3.2340
Max Act: 2.9502. Min Act: -0.1700
Data Index: 723161 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2340. Min Range: -3.2340
Max Act: 2.9502. Min Act: -0.1700
Data Index: 7558903 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #19