Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2903 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.2434. Min Range: -4.2434
Max Act: 4.2434. Min Act: -0.1700
Data Index: 7938208 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2434. Min Range: -4.2434
Max Act: 4.2121. Min Act: -0.1700
Data Index: 1593953 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2434. Min Range: -4.2434
Max Act: 4.1809. Min Act: -0.1700
Data Index: 3545815 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2434. Min Range: -4.2434
Max Act: 4.1496. Min Act: -0.1700
Data Index: 7622804 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2434. Min Range: -4.2434
Max Act: 4.0871. Min Act: -0.1700
Data Index: 2454620 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2434. Min Range: -4.2434
Max Act: 4.0246. Min Act: -0.1700
Data Index: 955839 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2434. Min Range: -4.2434
Max Act: 4.0559. Min Act: -0.1700
Data Index: 2027603 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2434. Min Range: -4.2434
Max Act: 4.0559. Min Act: -0.1700
Data Index: 3570473 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2434. Min Range: -4.2434
Max Act: 3.9777. Min Act: -0.1700
Data Index: 6916499 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2434. Min Range: -4.2434
Max Act: 3.9465. Min Act: -0.1700
Data Index: 7501330 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2434. Min Range: -4.2434
Max Act: 3.9308. Min Act: -0.1700
Data Index: 8335738 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2434. Min Range: -4.2434
Max Act: 3.9308. Min Act: -0.1700
Data Index: 64767 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2434. Min Range: -4.2434
Max Act: 3.9465. Min Act: -0.1700
Data Index: 7781112 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2434. Min Range: -4.2434
Max Act: 3.9308. Min Act: -0.1700
Data Index: 2331481 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2434. Min Range: -4.2434
Max Act: 3.9152. Min Act: -0.1700
Data Index: 8606369 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2434. Min Range: -4.2434
Max Act: 3.8996. Min Act: -0.1700
Data Index: 5752796 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2434. Min Range: -4.2434
Max Act: 3.8996. Min Act: -0.1700
Data Index: 1947754 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2434. Min Range: -4.2434
Max Act: 3.9152. Min Act: -0.1700
Data Index: 4210733 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2434. Min Range: -4.2434
Max Act: 3.9152. Min Act: -0.1700
Data Index: 7632972 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2434. Min Range: -4.2434
Max Act: 3.8839. Min Act: -0.1700
Data Index: 225852 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #19