Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2980 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.9217. Min Range: -5.9217
Max Act: 5.9217. Min Act: -0.1700
Data Index: 4724658 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9217. Min Range: -5.9217
Max Act: 5.8592. Min Act: -0.1700
Data Index: 4675471 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9217. Min Range: -5.9217
Max Act: 5.8279. Min Act: -0.1700
Data Index: 6211242 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9217. Min Range: -5.9217
Max Act: 5.6404. Min Act: -0.1700
Data Index: 5066365 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9217. Min Range: -5.9217
Max Act: 5.5467. Min Act: -0.1700
Data Index: 8759634 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9217. Min Range: -5.9217
Max Act: 5.5154. Min Act: -0.1700
Data Index: 8198781 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9217. Min Range: -5.9217
Max Act: 5.5154. Min Act: -0.1700
Data Index: 3404062 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9217. Min Range: -5.9217
Max Act: 5.4529. Min Act: -0.1700
Data Index: 996745 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9217. Min Range: -5.9217
Max Act: 5.4529. Min Act: -0.1700
Data Index: 3145866 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9217. Min Range: -5.9217
Max Act: 5.4217. Min Act: -0.1700
Data Index: 3421084 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9217. Min Range: -5.9217
Max Act: 5.3904. Min Act: -0.1700
Data Index: 2935425 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9217. Min Range: -5.9217
Max Act: 5.3904. Min Act: -0.1700
Data Index: 7256817 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9217. Min Range: -5.9217
Max Act: 5.3592. Min Act: -0.1700
Data Index: 4493879 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9217. Min Range: -5.9217
Max Act: 5.3904. Min Act: -0.1700
Data Index: 5228339 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9217. Min Range: -5.9217
Max Act: 5.3279. Min Act: -0.1700
Data Index: 3166635 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9217. Min Range: -5.9217
Max Act: 5.3592. Min Act: -0.1700
Data Index: 3189921 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9217. Min Range: -5.9217
Max Act: 5.3592. Min Act: -0.1700
Data Index: 6247341 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9217. Min Range: -5.9217
Max Act: 5.3279. Min Act: -0.1700
Data Index: 4443034 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9217. Min Range: -5.9217
Max Act: 5.3279. Min Act: -0.1700
Data Index: 616105 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9217. Min Range: -5.9217
Max Act: 5.3279. Min Act: -0.1700
Data Index: 707637 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #19