Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2015 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2170. Min Range: -8.2170
Max Act: 8.2170. Min Act: -0.1700
Data Index: 441734 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2170. Min Range: -8.2170
Max Act: 8.1545. Min Act: -0.1700
Data Index: 5953796 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2170. Min Range: -8.2170
Max Act: 7.9670. Min Act: -0.1700
Data Index: 3805221 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2170. Min Range: -8.2170
Max Act: 7.9045. Min Act: -0.1700
Data Index: 5599764 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2170. Min Range: -8.2170
Max Act: 7.7482. Min Act: -0.1700
Data Index: 5423437 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2170. Min Range: -8.2170
Max Act: 7.7170. Min Act: -0.1700
Data Index: 4593813 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2170. Min Range: -8.2170
Max Act: 7.6545. Min Act: -0.1700
Data Index: 5599761 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2170. Min Range: -8.2170
Max Act: 7.6545. Min Act: -0.1700
Data Index: 2687605 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2170. Min Range: -8.2170
Max Act: 7.6232. Min Act: -0.1700
Data Index: 8035489 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2170. Min Range: -8.2170
Max Act: 7.4982. Min Act: -0.1700
Data Index: 5599765 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2170. Min Range: -8.2170
Max Act: 7.4670. Min Act: -0.1700
Data Index: 6406998 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2170. Min Range: -8.2170
Max Act: 7.4670. Min Act: -0.1700
Data Index: 5453806 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2170. Min Range: -8.2170
Max Act: 7.4670. Min Act: -0.1700
Data Index: 3531718 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2170. Min Range: -8.2170
Max Act: 7.4357. Min Act: -0.1700
Data Index: 7121115 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2170. Min Range: -8.2170
Max Act: 7.4045. Min Act: -0.1700
Data Index: 3591267 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2170. Min Range: -8.2170
Max Act: 7.3732. Min Act: -0.1700
Data Index: 1094641 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2170. Min Range: -8.2170
Max Act: 7.3420. Min Act: -0.1700
Data Index: 5599762 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2170. Min Range: -8.2170
Max Act: 7.3107. Min Act: -0.1700
Data Index: 98104 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2170. Min Range: -8.2170
Max Act: 7.3107. Min Act: -0.1700
Data Index: 2983690 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2170. Min Range: -8.2170
Max Act: 7.3107. Min Act: -0.1700
Data Index: 1785525 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #19