Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3991 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.5428. Min Range: -5.5428
Max Act: 5.5428. Min Act: -0.1700
Data Index: 4838442 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5428. Min Range: -5.5428
Max Act: 5.5428. Min Act: -0.1700
Data Index: 702200 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5428. Min Range: -5.5428
Max Act: 5.5116. Min Act: -0.1700
Data Index: 8186484 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5428. Min Range: -5.5428
Max Act: 5.5428. Min Act: -0.1700
Data Index: 2339546 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5428. Min Range: -5.5428
Max Act: 5.5116. Min Act: -0.1700
Data Index: 7066494 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5428. Min Range: -5.5428
Max Act: 5.4803. Min Act: -0.1700
Data Index: 2272252 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5428. Min Range: -5.5428
Max Act: 5.5428. Min Act: -0.1700
Data Index: 8501163 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5428. Min Range: -5.5428
Max Act: 5.4491. Min Act: -0.1700
Data Index: 1122746 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5428. Min Range: -5.5428
Max Act: 5.4491. Min Act: -0.1700
Data Index: 7207095 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5428. Min Range: -5.5428
Max Act: 5.4491. Min Act: -0.1700
Data Index: 4920986 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5428. Min Range: -5.5428
Max Act: 5.4803. Min Act: -0.1700
Data Index: 2175803 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5428. Min Range: -5.5428
Max Act: 5.4803. Min Act: -0.1700
Data Index: 950144 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5428. Min Range: -5.5428
Max Act: 5.4491. Min Act: -0.1700
Data Index: 8218097 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5428. Min Range: -5.5428
Max Act: 5.5116. Min Act: -0.1700
Data Index: 2526365 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5428. Min Range: -5.5428
Max Act: 5.4491. Min Act: -0.1700
Data Index: 4757940 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5428. Min Range: -5.5428
Max Act: 5.4178. Min Act: -0.1700
Data Index: 3425724 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5428. Min Range: -5.5428
Max Act: 5.3553. Min Act: -0.1700
Data Index: 6543834 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5428. Min Range: -5.5428
Max Act: 5.4178. Min Act: -0.1700
Data Index: 1522923 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5428. Min Range: -5.5428
Max Act: 5.4178. Min Act: -0.1700
Data Index: 8328615 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5428. Min Range: -5.5428
Max Act: 5.4491. Min Act: -0.1700
Data Index: 3075802 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #19