Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2364 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.5776. Min Range: -8.5776
Max Act: 8.5776. Min Act: -0.1700
Data Index: 7636243 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5776. Min Range: -8.5776
Max Act: 8.5151. Min Act: -0.1700
Data Index: 6029761 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5776. Min Range: -8.5776
Max Act: 8.4526. Min Act: -0.1700
Data Index: 3057396 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5776. Min Range: -8.5776
Max Act: 8.3901. Min Act: -0.1700
Data Index: 13365 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5776. Min Range: -8.5776
Max Act: 8.2651. Min Act: -0.1700
Data Index: 2805699 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5776. Min Range: -8.5776
Max Act: 8.2651. Min Act: -0.1700
Data Index: 8504187 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5776. Min Range: -8.5776
Max Act: 8.1401. Min Act: -0.1700
Data Index: 8744315 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5776. Min Range: -8.5776
Max Act: 8.0776. Min Act: -0.1700
Data Index: 678864 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5776. Min Range: -8.5776
Max Act: 8.0776. Min Act: -0.1700
Data Index: 2966829 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5776. Min Range: -8.5776
Max Act: 8.0151. Min Act: -0.1700
Data Index: 6460694 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5776. Min Range: -8.5776
Max Act: 8.0151. Min Act: -0.1700
Data Index: 1919225 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5776. Min Range: -8.5776
Max Act: 8.0151. Min Act: -0.1700
Data Index: 4891686 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5776. Min Range: -8.5776
Max Act: 7.9526. Min Act: -0.1700
Data Index: 4719834 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5776. Min Range: -8.5776
Max Act: 7.9526. Min Act: -0.1700
Data Index: 991305 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5776. Min Range: -8.5776
Max Act: 8.0151. Min Act: -0.1700
Data Index: 1258297 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5776. Min Range: -8.5776
Max Act: 7.8901. Min Act: -0.1700
Data Index: 3286866 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5776. Min Range: -8.5776
Max Act: 7.8901. Min Act: -0.1700
Data Index: 8295073 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5776. Min Range: -8.5776
Max Act: 7.8901. Min Act: -0.1700
Data Index: 1683068 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5776. Min Range: -8.5776
Max Act: 7.8589. Min Act: -0.1700
Data Index: 5113195 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5776. Min Range: -8.5776
Max Act: 7.8589. Min Act: -0.1700
Data Index: 4021614 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #19