Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4221 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.6126. Min Range: -4.6126
Max Act: 4.6126. Min Act: -0.1700
Data Index: 3745028 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6126. Min Range: -4.6126
Max Act: 4.5188. Min Act: -0.1700
Data Index: 5183023 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6126. Min Range: -4.6126
Max Act: 4.4563. Min Act: -0.1700
Data Index: 5520879 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6126. Min Range: -4.6126
Max Act: 4.4251. Min Act: -0.1700
Data Index: 451725 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6126. Min Range: -4.6126
Max Act: 4.3938. Min Act: -0.1700
Data Index: 3076151 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6126. Min Range: -4.6126
Max Act: 4.3626. Min Act: -0.1700
Data Index: 2060313 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6126. Min Range: -4.6126
Max Act: 4.3626. Min Act: -0.1700
Data Index: 8757977 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6126. Min Range: -4.6126
Max Act: 4.3626. Min Act: -0.1700
Data Index: 1981734 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6126. Min Range: -4.6126
Max Act: 4.3001. Min Act: -0.1700
Data Index: 3566192 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6126. Min Range: -4.6126
Max Act: 4.3313. Min Act: -0.1700
Data Index: 7434037 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6126. Min Range: -4.6126
Max Act: 4.3313. Min Act: -0.1700
Data Index: 2874289 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6126. Min Range: -4.6126
Max Act: 4.3313. Min Act: -0.1700
Data Index: 3592806 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6126. Min Range: -4.6126
Max Act: 4.3001. Min Act: -0.1700
Data Index: 6599158 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6126. Min Range: -4.6126
Max Act: 4.3001. Min Act: -0.1700
Data Index: 4681866 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6126. Min Range: -4.6126
Max Act: 4.2688. Min Act: -0.1700
Data Index: 690267 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6126. Min Range: -4.6126
Max Act: 4.2688. Min Act: -0.1700
Data Index: 5544502 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6126. Min Range: -4.6126
Max Act: 4.2688. Min Act: -0.1700
Data Index: 8440308 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6126. Min Range: -4.6126
Max Act: 4.2688. Min Act: -0.1700
Data Index: 8489894 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6126. Min Range: -4.6126
Max Act: 4.2688. Min Act: -0.1700
Data Index: 2207115 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6126. Min Range: -4.6126
Max Act: 4.2688. Min Act: -0.1700
Data Index: 7998964 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #19