Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2676 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7676. Min Range: -5.7676
Max Act: 5.7676. Min Act: -0.1700
Data Index: 1851539 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7676. Min Range: -5.7676
Max Act: 5.7051. Min Act: -0.1700
Data Index: 2709029 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7676. Min Range: -5.7676
Max Act: 5.6426. Min Act: -0.1700
Data Index: 2307237 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7676. Min Range: -5.7676
Max Act: 5.6426. Min Act: -0.1700
Data Index: 6225080 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7676. Min Range: -5.7676
Max Act: 5.6426. Min Act: -0.1700
Data Index: 3080438 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7676. Min Range: -5.7676
Max Act: 5.6426. Min Act: -0.1700
Data Index: 7556848 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7676. Min Range: -5.7676
Max Act: 5.6426. Min Act: -0.1700
Data Index: 2538819 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7676. Min Range: -5.7676
Max Act: 5.5801. Min Act: -0.1700
Data Index: 3572719 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7676. Min Range: -5.7676
Max Act: 5.4863. Min Act: -0.1700
Data Index: 6374105 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7676. Min Range: -5.7676
Max Act: 5.4551. Min Act: -0.1700
Data Index: 7782039 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7676. Min Range: -5.7676
Max Act: 5.4551. Min Act: -0.1700
Data Index: 1516424 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7676. Min Range: -5.7676
Max Act: 5.4551. Min Act: -0.1700
Data Index: 631291 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7676. Min Range: -5.7676
Max Act: 5.4551. Min Act: -0.1700
Data Index: 263401 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7676. Min Range: -5.7676
Max Act: 5.4238. Min Act: -0.1700
Data Index: 3723008 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7676. Min Range: -5.7676
Max Act: 5.4238. Min Act: -0.1700
Data Index: 1523471 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7676. Min Range: -5.7676
Max Act: 5.4238. Min Act: -0.1700
Data Index: 7880699 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7676. Min Range: -5.7676
Max Act: 5.4238. Min Act: -0.1700
Data Index: 6586510 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7676. Min Range: -5.7676
Max Act: 5.4238. Min Act: -0.1700
Data Index: 7531657 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7676. Min Range: -5.7676
Max Act: 5.3926. Min Act: -0.1700
Data Index: 4808106 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7676. Min Range: -5.7676
Max Act: 5.3926. Min Act: -0.1700
Data Index: 6851293 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #19