Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3318 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.3413. Min Range: -3.3413
Max Act: 3.3413. Min Act: -0.1700
Data Index: 552396 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3413. Min Range: -3.3413
Max Act: 3.2785. Min Act: -0.1700
Data Index: 2678648 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3413. Min Range: -3.3413
Max Act: 3.2000. Min Act: -0.1700
Data Index: 2678647 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3413. Min Range: -3.3413
Max Act: 3.1685. Min Act: -0.1700
Data Index: 7580798 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3413. Min Range: -3.3413
Max Act: 3.1370. Min Act: -0.1700
Data Index: 2678655 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3413. Min Range: -3.3413
Max Act: 3.1055. Min Act: -0.1700
Data Index: 8560949 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3413. Min Range: -3.3413
Max Act: 3.1213. Min Act: -0.1700
Data Index: 3083849 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3413. Min Range: -3.3413
Max Act: 3.0898. Min Act: -0.1700
Data Index: 2678645 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3413. Min Range: -3.3413
Max Act: 3.1055. Min Act: -0.1700
Data Index: 1440709 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3413. Min Range: -3.3413
Max Act: 3.0740. Min Act: -0.1700
Data Index: 2254146 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3413. Min Range: -3.3413
Max Act: 3.0740. Min Act: -0.1700
Data Index: 1261669 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3413. Min Range: -3.3413
Max Act: 3.0582. Min Act: -0.1700
Data Index: 2148805 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3413. Min Range: -3.3413
Max Act: 3.0424. Min Act: -0.1700
Data Index: 6866267 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3413. Min Range: -3.3413
Max Act: 3.0424. Min Act: -0.1700
Data Index: 6750668 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3413. Min Range: -3.3413
Max Act: 3.0267. Min Act: -0.1700
Data Index: 589992 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3413. Min Range: -3.3413
Max Act: 3.0267. Min Act: -0.1700
Data Index: 2678657 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3413. Min Range: -3.3413
Max Act: 3.0267. Min Act: -0.1700
Data Index: 6760173 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3413. Min Range: -3.3413
Max Act: 2.9951. Min Act: -0.1700
Data Index: 974931 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3413. Min Range: -3.3413
Max Act: 3.0267. Min Act: -0.1700
Data Index: 5569530 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3413. Min Range: -3.3413
Max Act: 3.0109. Min Act: -0.1700
Data Index: 4039091 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #19