Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2968 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9830. Min Range: -6.9830
Max Act: 6.9830. Min Act: -0.1700
Data Index: 5276979 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9830. Min Range: -6.9830
Max Act: 6.9830. Min Act: -0.1700
Data Index: 7134704 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9830. Min Range: -6.9830
Max Act: 6.9205. Min Act: -0.1700
Data Index: 859047 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9830. Min Range: -6.9830
Max Act: 6.8892. Min Act: -0.1700
Data Index: 1570152 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9830. Min Range: -6.9830
Max Act: 6.8267. Min Act: -0.1700
Data Index: 394886 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9830. Min Range: -6.9830
Max Act: 6.8267. Min Act: -0.1700
Data Index: 389918 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9830. Min Range: -6.9830
Max Act: 6.7642. Min Act: -0.1700
Data Index: 756950 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9830. Min Range: -6.9830
Max Act: 6.6705. Min Act: -0.1700
Data Index: 4458077 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9830. Min Range: -6.9830
Max Act: 6.6392. Min Act: -0.1700
Data Index: 4008143 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9830. Min Range: -6.9830
Max Act: 6.6705. Min Act: -0.1700
Data Index: 6313051 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9830. Min Range: -6.9830
Max Act: 6.6080. Min Act: -0.1700
Data Index: 4212914 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9830. Min Range: -6.9830
Max Act: 6.6080. Min Act: -0.1700
Data Index: 6397906 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9830. Min Range: -6.9830
Max Act: 6.6080. Min Act: -0.1700
Data Index: 5955581 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9830. Min Range: -6.9830
Max Act: 6.6080. Min Act: -0.1700
Data Index: 2102158 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9830. Min Range: -6.9830
Max Act: 6.5767. Min Act: -0.1700
Data Index: 1272476 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9830. Min Range: -6.9830
Max Act: 6.5767. Min Act: -0.1700
Data Index: 5770287 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9830. Min Range: -6.9830
Max Act: 6.5455. Min Act: -0.1700
Data Index: 676751 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9830. Min Range: -6.9830
Max Act: 6.5455. Min Act: -0.1700
Data Index: 1289063 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9830. Min Range: -6.9830
Max Act: 6.5455. Min Act: -0.1700
Data Index: 5627471 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9830. Min Range: -6.9830
Max Act: 6.4830. Min Act: -0.1700
Data Index: 4977069 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #19