Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4768 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8360. Min Range: -5.8360
Max Act: 5.8360. Min Act: -0.1700
Data Index: 8018920 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8360. Min Range: -5.8360
Max Act: 5.6485. Min Act: -0.1700
Data Index: 1945106 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8360. Min Range: -5.8360
Max Act: 5.5547. Min Act: -0.1700
Data Index: 8414767 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8360. Min Range: -5.8360
Max Act: 5.4922. Min Act: -0.1700
Data Index: 6882447 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8360. Min Range: -5.8360
Max Act: 5.4610. Min Act: -0.1700
Data Index: 6900354 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8360. Min Range: -5.8360
Max Act: 5.4297. Min Act: -0.1700
Data Index: 7678287 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8360. Min Range: -5.8360
Max Act: 5.4297. Min Act: -0.1700
Data Index: 673746 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8360. Min Range: -5.8360
Max Act: 5.3985. Min Act: -0.1700
Data Index: 6059081 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8360. Min Range: -5.8360
Max Act: 5.3672. Min Act: -0.1700
Data Index: 7529975 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8360. Min Range: -5.8360
Max Act: 5.3360. Min Act: -0.1700
Data Index: 3393832 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8360. Min Range: -5.8360
Max Act: 5.3360. Min Act: -0.1700
Data Index: 6258527 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8360. Min Range: -5.8360
Max Act: 5.3360. Min Act: -0.1700
Data Index: 2993902 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8360. Min Range: -5.8360
Max Act: 5.3360. Min Act: -0.1700
Data Index: 4032108 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8360. Min Range: -5.8360
Max Act: 5.3047. Min Act: -0.1700
Data Index: 1920506 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8360. Min Range: -5.8360
Max Act: 5.3047. Min Act: -0.1700
Data Index: 4566989 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8360. Min Range: -5.8360
Max Act: 5.3047. Min Act: -0.1700
Data Index: 4334410 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8360. Min Range: -5.8360
Max Act: 5.2735. Min Act: -0.1700
Data Index: 3401069 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8360. Min Range: -5.8360
Max Act: 5.2735. Min Act: -0.1700
Data Index: 1053926 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8360. Min Range: -5.8360
Max Act: 5.2422. Min Act: -0.1700
Data Index: 7206418 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8360. Min Range: -5.8360
Max Act: 5.2422. Min Act: -0.1700
Data Index: 3049174 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #19