Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2169 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 16.1433. Min Range: -16.1433
Max Act: 16.1433. Min Act: -0.1700
Data Index: 3277503 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 16.1433. Min Range: -16.1433
Max Act: 16.0183. Min Act: -0.1700
Data Index: 5418519 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 16.1433. Min Range: -16.1433
Max Act: 16.0183. Min Act: -0.1700
Data Index: 8251891 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 16.1433. Min Range: -16.1433
Max Act: 15.7683. Min Act: -0.1700
Data Index: 6945618 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 16.1433. Min Range: -16.1433
Max Act: 15.7683. Min Act: -0.1700
Data Index: 5509039 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 16.1433. Min Range: -16.1433
Max Act: 15.7683. Min Act: -0.1700
Data Index: 6072418 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 16.1433. Min Range: -16.1433
Max Act: 15.7683. Min Act: -0.1700
Data Index: 694691 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 16.1433. Min Range: -16.1433
Max Act: 15.6433. Min Act: -0.1700
Data Index: 5509995 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 16.1433. Min Range: -16.1433
Max Act: 15.6433. Min Act: -0.1700
Data Index: 2328540 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 16.1433. Min Range: -16.1433
Max Act: 15.6433. Min Act: -0.1700
Data Index: 3284496 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 16.1433. Min Range: -16.1433
Max Act: 15.5183. Min Act: -0.1700
Data Index: 2180674 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 16.1433. Min Range: -16.1433
Max Act: 15.5183. Min Act: -0.1700
Data Index: 5799909 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 16.1433. Min Range: -16.1433
Max Act: 15.5183. Min Act: -0.1700
Data Index: 620283 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 16.1433. Min Range: -16.1433
Max Act: 15.6433. Min Act: -0.1700
Data Index: 3721154 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 16.1433. Min Range: -16.1433
Max Act: 15.5183. Min Act: -0.1700
Data Index: 2425864 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 16.1433. Min Range: -16.1433
Max Act: 15.4558. Min Act: -0.1700
Data Index: 3662349 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 16.1433. Min Range: -16.1433
Max Act: 15.3933. Min Act: -0.1700
Data Index: 3813381 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 16.1433. Min Range: -16.1433
Max Act: 15.4558. Min Act: -0.1700
Data Index: 6556248 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 16.1433. Min Range: -16.1433
Max Act: 15.3933. Min Act: -0.1700
Data Index: 3306690 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 16.1433. Min Range: -16.1433
Max Act: 15.3933. Min Act: -0.1700
Data Index: 4449563 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #19