Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5109 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3084. Min Range: -9.3084
Max Act: 9.3084. Min Act: -0.1700
Data Index: 1406353 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3084. Min Range: -9.3084
Max Act: 9.0584. Min Act: -0.1700
Data Index: 4932115 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3084. Min Range: -9.3084
Max Act: 9.0584. Min Act: -0.1700
Data Index: 601338 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3084. Min Range: -9.3084
Max Act: 8.9334. Min Act: -0.1700
Data Index: 2066264 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3084. Min Range: -9.3084
Max Act: 8.8709. Min Act: -0.1700
Data Index: 1036954 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3084. Min Range: -9.3084
Max Act: 8.8084. Min Act: -0.1700
Data Index: 4863888 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3084. Min Range: -9.3084
Max Act: 8.6834. Min Act: -0.1700
Data Index: 5081089 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3084. Min Range: -9.3084
Max Act: 8.6834. Min Act: -0.1700
Data Index: 2285987 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3084. Min Range: -9.3084
Max Act: 8.6209. Min Act: -0.1700
Data Index: 1473779 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3084. Min Range: -9.3084
Max Act: 8.5584. Min Act: -0.1700
Data Index: 708147 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3084. Min Range: -9.3084
Max Act: 8.4959. Min Act: -0.1700
Data Index: 591234 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3084. Min Range: -9.3084
Max Act: 8.4334. Min Act: -0.1700
Data Index: 3999344 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3084. Min Range: -9.3084
Max Act: 8.2459. Min Act: -0.1700
Data Index: 386368 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3084. Min Range: -9.3084
Max Act: 8.3084. Min Act: -0.1700
Data Index: 4866425 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3084. Min Range: -9.3084
Max Act: 8.2459. Min Act: -0.1700
Data Index: 4126368 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3084. Min Range: -9.3084
Max Act: 8.2459. Min Act: -0.1700
Data Index: 6484439 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3084. Min Range: -9.3084
Max Act: 8.2459. Min Act: -0.1700
Data Index: 7145147 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3084. Min Range: -9.3084
Max Act: 8.1834. Min Act: -0.1700
Data Index: 6484438 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3084. Min Range: -9.3084
Max Act: 8.1834. Min Act: -0.1700
Data Index: 5197160 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3084. Min Range: -9.3084
Max Act: 8.1834. Min Act: -0.1700
Data Index: 3083540 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #19