Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4208 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6353. Min Range: -4.6353
Max Act: 4.6353. Min Act: -0.1700
Data Index: 276665 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6353. Min Range: -4.6353
Max Act: 4.6353. Min Act: -0.1700
Data Index: 3182769 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6353. Min Range: -4.6353
Max Act: 4.5728. Min Act: -0.1700
Data Index: 4655422 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6353. Min Range: -4.6353
Max Act: 4.4790. Min Act: -0.1700
Data Index: 4036738 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6353. Min Range: -4.6353
Max Act: 4.4790. Min Act: -0.1700
Data Index: 8139169 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6353. Min Range: -4.6353
Max Act: 4.4478. Min Act: -0.1700
Data Index: 3775320 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6353. Min Range: -4.6353
Max Act: 4.4478. Min Act: -0.1700
Data Index: 462176 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6353. Min Range: -4.6353
Max Act: 4.4165. Min Act: -0.1700
Data Index: 4875039 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6353. Min Range: -4.6353
Max Act: 4.4478. Min Act: -0.1700
Data Index: 8818964 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6353. Min Range: -4.6353
Max Act: 4.4165. Min Act: -0.1700
Data Index: 1117759 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6353. Min Range: -4.6353
Max Act: 4.4165. Min Act: -0.1700
Data Index: 2019464 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6353. Min Range: -4.6353
Max Act: 4.4165. Min Act: -0.1700
Data Index: 5767806 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6353. Min Range: -4.6353
Max Act: 4.4165. Min Act: -0.1700
Data Index: 7061306 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6353. Min Range: -4.6353
Max Act: 4.3853. Min Act: -0.1700
Data Index: 525892 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6353. Min Range: -4.6353
Max Act: 4.3853. Min Act: -0.1700
Data Index: 2052509 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6353. Min Range: -4.6353
Max Act: 4.3853. Min Act: -0.1700
Data Index: 2506187 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6353. Min Range: -4.6353
Max Act: 4.4165. Min Act: -0.1700
Data Index: 2052511 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6353. Min Range: -4.6353
Max Act: 4.3853. Min Act: -0.1700
Data Index: 4344551 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6353. Min Range: -4.6353
Max Act: 4.3853. Min Act: -0.1700
Data Index: 5079574 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6353. Min Range: -4.6353
Max Act: 4.3853. Min Act: -0.1700
Data Index: 1685042 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #19