Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1984 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.8954. Min Range: -3.8954
Max Act: 3.8954. Min Act: -0.1700
Data Index: 6113274 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8954. Min Range: -3.8954
Max Act: 3.8641. Min Act: -0.1700
Data Index: 8211333 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8954. Min Range: -3.8954
Max Act: 3.8641. Min Act: -0.1700
Data Index: 6570980 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8954. Min Range: -3.8954
Max Act: 3.8016. Min Act: -0.1700
Data Index: 7594829 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8954. Min Range: -3.8954
Max Act: 3.7546. Min Act: -0.1700
Data Index: 4881068 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8954. Min Range: -3.8954
Max Act: 3.7703. Min Act: -0.1700
Data Index: 8452558 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8954. Min Range: -3.8954
Max Act: 3.7703. Min Act: -0.1700
Data Index: 780837 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8954. Min Range: -3.8954
Max Act: 3.7546. Min Act: -0.1700
Data Index: 2076296 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8954. Min Range: -3.8954
Max Act: 3.7234. Min Act: -0.1700
Data Index: 2993931 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8954. Min Range: -3.8954
Max Act: 3.7546. Min Act: -0.1700
Data Index: 4175327 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8954. Min Range: -3.8954
Max Act: 3.7390. Min Act: -0.1700
Data Index: 802887 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8954. Min Range: -3.8954
Max Act: 3.7234. Min Act: -0.1700
Data Index: 7881376 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8954. Min Range: -3.8954
Max Act: 3.7234. Min Act: -0.1700
Data Index: 302701 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8954. Min Range: -3.8954
Max Act: 3.6921. Min Act: -0.1700
Data Index: 2993918 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8954. Min Range: -3.8954
Max Act: 3.7077. Min Act: -0.1700
Data Index: 1638813 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8954. Min Range: -3.8954
Max Act: 3.6921. Min Act: -0.1700
Data Index: 1077241 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8954. Min Range: -3.8954
Max Act: 3.6921. Min Act: -0.1700
Data Index: 56550 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8954. Min Range: -3.8954
Max Act: 3.6921. Min Act: -0.1700
Data Index: 8457383 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8954. Min Range: -3.8954
Max Act: 3.6608. Min Act: -0.1700
Data Index: 3627779 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8954. Min Range: -3.8954
Max Act: 3.6608. Min Act: -0.1700
Data Index: 2188961 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #19