Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3278 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9521. Min Range: -6.9521
Max Act: 6.9521. Min Act: -0.1700
Data Index: 4851501 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9521. Min Range: -6.9521
Max Act: 6.9521. Min Act: -0.1700
Data Index: 6872798 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9521. Min Range: -6.9521
Max Act: 6.9521. Min Act: -0.1700
Data Index: 5284162 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9521. Min Range: -6.9521
Max Act: 6.8271. Min Act: -0.1700
Data Index: 2916204 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9521. Min Range: -6.9521
Max Act: 6.8271. Min Act: -0.1700
Data Index: 1034949 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9521. Min Range: -6.9521
Max Act: 6.7334. Min Act: -0.1700
Data Index: 3442782 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9521. Min Range: -6.9521
Max Act: 6.7021. Min Act: -0.1700
Data Index: 7067281 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9521. Min Range: -6.9521
Max Act: 6.7021. Min Act: -0.1700
Data Index: 2945992 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9521. Min Range: -6.9521
Max Act: 6.6709. Min Act: -0.1700
Data Index: 5254624 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9521. Min Range: -6.9521
Max Act: 6.6709. Min Act: -0.1700
Data Index: 1015667 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9521. Min Range: -6.9521
Max Act: 6.6709. Min Act: -0.1700
Data Index: 8251299 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9521. Min Range: -6.9521
Max Act: 6.6396. Min Act: -0.1700
Data Index: 1830384 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9521. Min Range: -6.9521
Max Act: 6.6084. Min Act: -0.1700
Data Index: 2084457 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9521. Min Range: -6.9521
Max Act: 6.5771. Min Act: -0.1700
Data Index: 3012993 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9521. Min Range: -6.9521
Max Act: 6.5771. Min Act: -0.1700
Data Index: 1715289 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9521. Min Range: -6.9521
Max Act: 6.5771. Min Act: -0.1700
Data Index: 7684752 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9521. Min Range: -6.9521
Max Act: 6.5459. Min Act: -0.1700
Data Index: 7894208 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9521. Min Range: -6.9521
Max Act: 6.5146. Min Act: -0.1700
Data Index: 6081531 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9521. Min Range: -6.9521
Max Act: 6.5146. Min Act: -0.1700
Data Index: 5147042 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9521. Min Range: -6.9521
Max Act: 6.5459. Min Act: -0.1700
Data Index: 5377624 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #19