Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2967 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1181. Min Range: -6.1181
Max Act: 6.1181. Min Act: -0.1700
Data Index: 5637808 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1181. Min Range: -6.1181
Max Act: 6.0556. Min Act: -0.1700
Data Index: 8196380 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1181. Min Range: -6.1181
Max Act: 6.0556. Min Act: -0.1700
Data Index: 6590685 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1181. Min Range: -6.1181
Max Act: 5.9306. Min Act: -0.1700
Data Index: 2893784 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1181. Min Range: -6.1181
Max Act: 5.8993. Min Act: -0.1700
Data Index: 3611266 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1181. Min Range: -6.1181
Max Act: 5.8681. Min Act: -0.1700
Data Index: 4609930 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1181. Min Range: -6.1181
Max Act: 5.7431. Min Act: -0.1700
Data Index: 86126 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1181. Min Range: -6.1181
Max Act: 5.7118. Min Act: -0.1700
Data Index: 1160334 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1181. Min Range: -6.1181
Max Act: 5.6806. Min Act: -0.1700
Data Index: 8314181 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1181. Min Range: -6.1181
Max Act: 5.6493. Min Act: -0.1700
Data Index: 8401104 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1181. Min Range: -6.1181
Max Act: 5.6806. Min Act: -0.1700
Data Index: 5036031 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1181. Min Range: -6.1181
Max Act: 5.6493. Min Act: -0.1700
Data Index: 2016955 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1181. Min Range: -6.1181
Max Act: 5.6181. Min Act: -0.1700
Data Index: 7488132 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1181. Min Range: -6.1181
Max Act: 5.6181. Min Act: -0.1700
Data Index: 1789132 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1181. Min Range: -6.1181
Max Act: 5.6181. Min Act: -0.1700
Data Index: 4768165 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1181. Min Range: -6.1181
Max Act: 5.6181. Min Act: -0.1700
Data Index: 794228 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1181. Min Range: -6.1181
Max Act: 5.5868. Min Act: -0.1700
Data Index: 8168361 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1181. Min Range: -6.1181
Max Act: 5.5868. Min Act: -0.1700
Data Index: 58247 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1181. Min Range: -6.1181
Max Act: 5.5868. Min Act: -0.1700
Data Index: 4278149 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1181. Min Range: -6.1181
Max Act: 5.5868. Min Act: -0.1700
Data Index: 4510032 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #19