Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5087 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3986. Min Range: -5.3986
Max Act: 5.3986. Min Act: -0.1700
Data Index: 6339927 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3986. Min Range: -5.3986
Max Act: 5.3674. Min Act: -0.1700
Data Index: 8017783 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3986. Min Range: -5.3986
Max Act: 5.3361. Min Act: -0.1700
Data Index: 4204346 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3986. Min Range: -5.3986
Max Act: 5.3049. Min Act: -0.1700
Data Index: 3408313 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3986. Min Range: -5.3986
Max Act: 5.3049. Min Act: -0.1700
Data Index: 659790 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3986. Min Range: -5.3986
Max Act: 5.2736. Min Act: -0.1700
Data Index: 7059845 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3986. Min Range: -5.3986
Max Act: 5.2736. Min Act: -0.1700
Data Index: 855600 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3986. Min Range: -5.3986
Max Act: 5.2736. Min Act: -0.1700
Data Index: 6043774 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3986. Min Range: -5.3986
Max Act: 5.2736. Min Act: -0.1700
Data Index: 3834858 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3986. Min Range: -5.3986
Max Act: 5.2424. Min Act: -0.1700
Data Index: 2910855 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3986. Min Range: -5.3986
Max Act: 5.2111. Min Act: -0.1700
Data Index: 224605 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3986. Min Range: -5.3986
Max Act: 5.1799. Min Act: -0.1700
Data Index: 2485151 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3986. Min Range: -5.3986
Max Act: 5.2111. Min Act: -0.1700
Data Index: 4028675 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3986. Min Range: -5.3986
Max Act: 5.1486. Min Act: -0.1700
Data Index: 8441212 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3986. Min Range: -5.3986
Max Act: 5.1486. Min Act: -0.1700
Data Index: 8441217 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3986. Min Range: -5.3986
Max Act: 5.1799. Min Act: -0.1700
Data Index: 6081266 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3986. Min Range: -5.3986
Max Act: 5.1486. Min Act: -0.1700
Data Index: 856547 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3986. Min Range: -5.3986
Max Act: 5.1486. Min Act: -0.1700
Data Index: 856543 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3986. Min Range: -5.3986
Max Act: 5.1486. Min Act: -0.1700
Data Index: 6552609 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3986. Min Range: -5.3986
Max Act: 5.1174. Min Act: -0.1700
Data Index: 6081283 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #19