Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4159 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.3600. Min Range: -3.3600
Max Act: 3.3600. Min Act: -0.1700
Data Index: 879672 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3600. Min Range: -3.3600
Max Act: 3.1558. Min Act: -0.1700
Data Index: 7929255 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3600. Min Range: -3.3600
Max Act: 3.1243. Min Act: -0.1700
Data Index: 4844944 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3600. Min Range: -3.3600
Max Act: 3.1401. Min Act: -0.1700
Data Index: 1530863 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3600. Min Range: -3.3600
Max Act: 3.1401. Min Act: -0.1700
Data Index: 3848662 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3600. Min Range: -3.3600
Max Act: 3.1401. Min Act: -0.1700
Data Index: 6216352 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3600. Min Range: -3.3600
Max Act: 3.1243. Min Act: -0.1700
Data Index: 6557671 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3600. Min Range: -3.3600
Max Act: 3.1086. Min Act: -0.1700
Data Index: 6210321 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3600. Min Range: -3.3600
Max Act: 3.0928. Min Act: -0.1700
Data Index: 7658367 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3600. Min Range: -3.3600
Max Act: 3.0928. Min Act: -0.1700
Data Index: 3163881 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3600. Min Range: -3.3600
Max Act: 3.0613. Min Act: -0.1700
Data Index: 7309017 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3600. Min Range: -3.3600
Max Act: 3.0928. Min Act: -0.1700
Data Index: 3733432 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3600. Min Range: -3.3600
Max Act: 3.0770. Min Act: -0.1700
Data Index: 6760173 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3600. Min Range: -3.3600
Max Act: 3.0770. Min Act: -0.1700
Data Index: 806399 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3600. Min Range: -3.3600
Max Act: 3.0613. Min Act: -0.1700
Data Index: 6073331 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3600. Min Range: -3.3600
Max Act: 3.0455. Min Act: -0.1700
Data Index: 7170902 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3600. Min Range: -3.3600
Max Act: 3.0297. Min Act: -0.1700
Data Index: 5747262 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3600. Min Range: -3.3600
Max Act: 3.0297. Min Act: -0.1700
Data Index: 6715600 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3600. Min Range: -3.3600
Max Act: 3.0455. Min Act: -0.1700
Data Index: 4189276 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3600. Min Range: -3.3600
Max Act: 3.0613. Min Act: -0.1700
Data Index: 3078054 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #19