Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3051 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7855. Min Range: -5.7855
Max Act: 5.7855. Min Act: -0.1700
Data Index: 8117945 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7855. Min Range: -5.7855
Max Act: 5.6918. Min Act: -0.1700
Data Index: 8795435 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7855. Min Range: -5.7855
Max Act: 5.6605. Min Act: -0.1700
Data Index: 4118255 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7855. Min Range: -5.7855
Max Act: 5.5980. Min Act: -0.1700
Data Index: 4767276 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7855. Min Range: -5.7855
Max Act: 5.5355. Min Act: -0.1700
Data Index: 5015812 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7855. Min Range: -5.7855
Max Act: 5.5355. Min Act: -0.1700
Data Index: 4494365 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7855. Min Range: -5.7855
Max Act: 5.5043. Min Act: -0.1700
Data Index: 2635068 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7855. Min Range: -5.7855
Max Act: 5.4730. Min Act: -0.1700
Data Index: 7330754 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7855. Min Range: -5.7855
Max Act: 5.4730. Min Act: -0.1700
Data Index: 5672950 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7855. Min Range: -5.7855
Max Act: 5.4105. Min Act: -0.1700
Data Index: 5065697 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7855. Min Range: -5.7855
Max Act: 5.4418. Min Act: -0.1700
Data Index: 5899886 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7855. Min Range: -5.7855
Max Act: 5.4730. Min Act: -0.1700
Data Index: 3454690 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7855. Min Range: -5.7855
Max Act: 5.4418. Min Act: -0.1700
Data Index: 162301 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7855. Min Range: -5.7855
Max Act: 5.4105. Min Act: -0.1700
Data Index: 7841895 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7855. Min Range: -5.7855
Max Act: 5.4105. Min Act: -0.1700
Data Index: 179338 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7855. Min Range: -5.7855
Max Act: 5.4105. Min Act: -0.1700
Data Index: 1898241 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7855. Min Range: -5.7855
Max Act: 5.4105. Min Act: -0.1700
Data Index: 8732635 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7855. Min Range: -5.7855
Max Act: 5.4105. Min Act: -0.1700
Data Index: 3052427 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7855. Min Range: -5.7855
Max Act: 5.3793. Min Act: -0.1700
Data Index: 3674194 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7855. Min Range: -5.7855
Max Act: 5.3793. Min Act: -0.1700
Data Index: 2783857 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #19