Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4071 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7117. Min Range: -6.7117
Max Act: 6.7117. Min Act: -0.1700
Data Index: 7348312 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7117. Min Range: -6.7117
Max Act: 6.3992. Min Act: -0.1700
Data Index: 1455459 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7117. Min Range: -6.7117
Max Act: 6.3055. Min Act: -0.1700
Data Index: 3585114 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7117. Min Range: -6.7117
Max Act: 6.2430. Min Act: -0.1700
Data Index: 1251205 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7117. Min Range: -6.7117
Max Act: 6.2117. Min Act: -0.1700
Data Index: 7937228 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7117. Min Range: -6.7117
Max Act: 6.2430. Min Act: -0.1700
Data Index: 517284 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7117. Min Range: -6.7117
Max Act: 6.2117. Min Act: -0.1700
Data Index: 7131120 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7117. Min Range: -6.7117
Max Act: 6.1805. Min Act: -0.1700
Data Index: 5517346 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7117. Min Range: -6.7117
Max Act: 6.0867. Min Act: -0.1700
Data Index: 3264188 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7117. Min Range: -6.7117
Max Act: 6.0867. Min Act: -0.1700
Data Index: 8178683 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7117. Min Range: -6.7117
Max Act: 6.0867. Min Act: -0.1700
Data Index: 4021601 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7117. Min Range: -6.7117
Max Act: 6.0555. Min Act: -0.1700
Data Index: 2873791 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7117. Min Range: -6.7117
Max Act: 6.0867. Min Act: -0.1700
Data Index: 3057620 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7117. Min Range: -6.7117
Max Act: 6.0242. Min Act: -0.1700
Data Index: 391346 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7117. Min Range: -6.7117
Max Act: 6.0242. Min Act: -0.1700
Data Index: 164672 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7117. Min Range: -6.7117
Max Act: 5.9617. Min Act: -0.1700
Data Index: 7625047 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7117. Min Range: -6.7117
Max Act: 5.9930. Min Act: -0.1700
Data Index: 4739500 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7117. Min Range: -6.7117
Max Act: 5.9930. Min Act: -0.1700
Data Index: 1661516 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7117. Min Range: -6.7117
Max Act: 5.9617. Min Act: -0.1700
Data Index: 2808899 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7117. Min Range: -6.7117
Max Act: 5.9617. Min Act: -0.1700
Data Index: 794543 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #19