Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1166 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.1496. Min Range: -5.1496
Max Act: 5.1496. Min Act: -0.1700
Data Index: 5854307 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1496. Min Range: -5.1496
Max Act: 4.5871. Min Act: -0.1700
Data Index: 4334188 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1496. Min Range: -5.1496
Max Act: 4.5558. Min Act: -0.1700
Data Index: 8248069 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1496. Min Range: -5.1496
Max Act: 4.4933. Min Act: -0.1700
Data Index: 6364163 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1496. Min Range: -5.1496
Max Act: 4.4621. Min Act: -0.1700
Data Index: 7874164 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1496. Min Range: -5.1496
Max Act: 4.4933. Min Act: -0.1700
Data Index: 4682009 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1496. Min Range: -5.1496
Max Act: 4.4308. Min Act: -0.1700
Data Index: 8209312 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1496. Min Range: -5.1496
Max Act: 4.3996. Min Act: -0.1700
Data Index: 8511300 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1496. Min Range: -5.1496
Max Act: 4.4308. Min Act: -0.1700
Data Index: 5267979 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1496. Min Range: -5.1496
Max Act: 4.4308. Min Act: -0.1700
Data Index: 5758005 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1496. Min Range: -5.1496
Max Act: 4.3683. Min Act: -0.1700
Data Index: 2181534 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1496. Min Range: -5.1496
Max Act: 4.3996. Min Act: -0.1700
Data Index: 6238959 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1496. Min Range: -5.1496
Max Act: 4.3683. Min Act: -0.1700
Data Index: 7000954 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1496. Min Range: -5.1496
Max Act: 4.3683. Min Act: -0.1700
Data Index: 8373412 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1496. Min Range: -5.1496
Max Act: 4.3371. Min Act: -0.1700
Data Index: 3180913 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1496. Min Range: -5.1496
Max Act: 4.3371. Min Act: -0.1700
Data Index: 6445534 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1496. Min Range: -5.1496
Max Act: 4.3683. Min Act: -0.1700
Data Index: 193715 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1496. Min Range: -5.1496
Max Act: 4.3371. Min Act: -0.1700
Data Index: 4804857 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1496. Min Range: -5.1496
Max Act: 4.3371. Min Act: -0.1700
Data Index: 7752506 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1496. Min Range: -5.1496
Max Act: 4.3371. Min Act: -0.1700
Data Index: 7941465 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #19