Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1658 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.9776. Min Range: -3.9776
Max Act: 3.9776. Min Act: -0.1700
Data Index: 3476907 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9776. Min Range: -3.9776
Max Act: 3.9776. Min Act: -0.1700
Data Index: 2692261 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9776. Min Range: -3.9776
Max Act: 3.9151. Min Act: -0.1700
Data Index: 463653 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9776. Min Range: -3.9776
Max Act: 3.8838. Min Act: -0.1700
Data Index: 2356448 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9776. Min Range: -3.9776
Max Act: 3.8525. Min Act: -0.1700
Data Index: 1767750 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9776. Min Range: -3.9776
Max Act: 3.8213. Min Act: -0.1700
Data Index: 2954099 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9776. Min Range: -3.9776
Max Act: 3.7900. Min Act: -0.1700
Data Index: 5930331 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9776. Min Range: -3.9776
Max Act: 3.7900. Min Act: -0.1700
Data Index: 1359871 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9776. Min Range: -3.9776
Max Act: 3.7274. Min Act: -0.1700
Data Index: 1013623 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9776. Min Range: -3.9776
Max Act: 3.7274. Min Act: -0.1700
Data Index: 352250 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9776. Min Range: -3.9776
Max Act: 3.7431. Min Act: -0.1700
Data Index: 3356706 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9776. Min Range: -3.9776
Max Act: 3.7274. Min Act: -0.1700
Data Index: 4044747 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9776. Min Range: -3.9776
Max Act: 3.7118. Min Act: -0.1700
Data Index: 7795517 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9776. Min Range: -3.9776
Max Act: 3.7118. Min Act: -0.1700
Data Index: 5494928 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9776. Min Range: -3.9776
Max Act: 3.6805. Min Act: -0.1700
Data Index: 7629356 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9776. Min Range: -3.9776
Max Act: 3.6962. Min Act: -0.1700
Data Index: 7179980 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9776. Min Range: -3.9776
Max Act: 3.6962. Min Act: -0.1700
Data Index: 3051712 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9776. Min Range: -3.9776
Max Act: 3.6649. Min Act: -0.1700
Data Index: 5512211 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9776. Min Range: -3.9776
Max Act: 3.6805. Min Act: -0.1700
Data Index: 7705432 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9776. Min Range: -3.9776
Max Act: 3.6649. Min Act: -0.1700
Data Index: 1518836 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #19