Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5536 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4879. Min Range: -5.4879
Max Act: 5.4879. Min Act: -0.1700
Data Index: 1494931 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4879. Min Range: -5.4879
Max Act: 5.3941. Min Act: -0.1700
Data Index: 5740297 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4879. Min Range: -5.4879
Max Act: 5.2691. Min Act: -0.1700
Data Index: 7365645 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4879. Min Range: -5.4879
Max Act: 5.2379. Min Act: -0.1700
Data Index: 7904299 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4879. Min Range: -5.4879
Max Act: 5.2379. Min Act: -0.1700
Data Index: 4789554 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4879. Min Range: -5.4879
Max Act: 5.2066. Min Act: -0.1700
Data Index: 3797391 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4879. Min Range: -5.4879
Max Act: 5.1754. Min Act: -0.1700
Data Index: 5446554 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4879. Min Range: -5.4879
Max Act: 5.1754. Min Act: -0.1700
Data Index: 3014446 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4879. Min Range: -5.4879
Max Act: 5.1441. Min Act: -0.1691
Data Index: 3314694 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4879. Min Range: -5.4879
Max Act: 5.1129. Min Act: -0.1700
Data Index: 7952935 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4879. Min Range: -5.4879
Max Act: 5.1129. Min Act: -0.1700
Data Index: 5561704 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4879. Min Range: -5.4879
Max Act: 5.0816. Min Act: -0.1700
Data Index: 2636119 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4879. Min Range: -5.4879
Max Act: 5.0816. Min Act: -0.1700
Data Index: 2930803 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4879. Min Range: -5.4879
Max Act: 5.0816. Min Act: -0.1700
Data Index: 7129672 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4879. Min Range: -5.4879
Max Act: 5.0816. Min Act: -0.1700
Data Index: 1938660 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4879. Min Range: -5.4879
Max Act: 5.0816. Min Act: -0.1700
Data Index: 2005933 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4879. Min Range: -5.4879
Max Act: 5.0504. Min Act: -0.1700
Data Index: 5740308 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4879. Min Range: -5.4879
Max Act: 5.0504. Min Act: -0.1700
Data Index: 6255061 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4879. Min Range: -5.4879
Max Act: 5.0504. Min Act: -0.1700
Data Index: 3455808 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4879. Min Range: -5.4879
Max Act: 5.0504. Min Act: -0.1700
Data Index: 924665 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #19