Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3113 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3046. Min Range: -8.3046
Max Act: 8.3046. Min Act: -0.1700
Data Index: 5833433 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3046. Min Range: -8.3046
Max Act: 7.9296. Min Act: -0.1700
Data Index: 6607783 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3046. Min Range: -8.3046
Max Act: 7.8984. Min Act: -0.1700
Data Index: 5515616 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3046. Min Range: -8.3046
Max Act: 7.8046. Min Act: -0.1700
Data Index: 962260 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3046. Min Range: -8.3046
Max Act: 7.8046. Min Act: -0.1700
Data Index: 4229607 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3046. Min Range: -8.3046
Max Act: 7.8046. Min Act: -0.1700
Data Index: 4466798 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3046. Min Range: -8.3046
Max Act: 7.6171. Min Act: -0.1700
Data Index: 2541510 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3046. Min Range: -8.3046
Max Act: 7.6171. Min Act: -0.1700
Data Index: 5059358 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3046. Min Range: -8.3046
Max Act: 7.5546. Min Act: -0.1700
Data Index: 6737349 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3046. Min Range: -8.3046
Max Act: 7.4609. Min Act: -0.1700
Data Index: 2460865 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3046. Min Range: -8.3046
Max Act: 7.4609. Min Act: -0.1700
Data Index: 6298838 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3046. Min Range: -8.3046
Max Act: 7.4609. Min Act: -0.1700
Data Index: 1881468 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3046. Min Range: -8.3046
Max Act: 7.3984. Min Act: -0.1700
Data Index: 2118599 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3046. Min Range: -8.3046
Max Act: 7.3984. Min Act: -0.1700
Data Index: 8348158 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3046. Min Range: -8.3046
Max Act: 7.3984. Min Act: -0.1700
Data Index: 6181763 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3046. Min Range: -8.3046
Max Act: 7.3046. Min Act: -0.1700
Data Index: 6796997 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3046. Min Range: -8.3046
Max Act: 7.3359. Min Act: -0.1700
Data Index: 8210474 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3046. Min Range: -8.3046
Max Act: 7.2734. Min Act: -0.1700
Data Index: 1347952 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3046. Min Range: -8.3046
Max Act: 7.2734. Min Act: -0.1700
Data Index: 6623414 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3046. Min Range: -8.3046
Max Act: 7.2109. Min Act: -0.1700
Data Index: 1472025 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #19