Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4764 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.7910. Min Range: -4.7910
Max Act: 4.7910. Min Act: -0.1700
Data Index: 1160108 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7910. Min Range: -4.7910
Max Act: 4.6972. Min Act: -0.1700
Data Index: 7983939 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7910. Min Range: -4.7910
Max Act: 4.5722. Min Act: -0.1700
Data Index: 8601604 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7910. Min Range: -4.7910
Max Act: 4.5722. Min Act: -0.1700
Data Index: 7741787 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7910. Min Range: -4.7910
Max Act: 4.5722. Min Act: -0.1700
Data Index: 1966704 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7910. Min Range: -4.7910
Max Act: 4.5410. Min Act: -0.1700
Data Index: 3457602 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7910. Min Range: -4.7910
Max Act: 4.5410. Min Act: -0.1700
Data Index: 5498038 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7910. Min Range: -4.7910
Max Act: 4.5097. Min Act: -0.1700
Data Index: 4088940 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7910. Min Range: -4.7910
Max Act: 4.5097. Min Act: -0.1700
Data Index: 4941948 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7910. Min Range: -4.7910
Max Act: 4.4785. Min Act: -0.1700
Data Index: 6608913 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7910. Min Range: -4.7910
Max Act: 4.4785. Min Act: -0.1700
Data Index: 8648593 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7910. Min Range: -4.7910
Max Act: 4.4472. Min Act: -0.1700
Data Index: 6025565 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7910. Min Range: -4.7910
Max Act: 4.4472. Min Act: -0.1700
Data Index: 4106393 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7910. Min Range: -4.7910
Max Act: 4.4160. Min Act: -0.1700
Data Index: 7765934 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7910. Min Range: -4.7910
Max Act: 4.4472. Min Act: -0.1700
Data Index: 3025945 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7910. Min Range: -4.7910
Max Act: 4.4160. Min Act: -0.1700
Data Index: 2199802 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7910. Min Range: -4.7910
Max Act: 4.4160. Min Act: -0.1700
Data Index: 1374431 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7910. Min Range: -4.7910
Max Act: 4.4160. Min Act: -0.1700
Data Index: 2800743 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7910. Min Range: -4.7910
Max Act: 4.4160. Min Act: -0.1700
Data Index: 8102734 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7910. Min Range: -4.7910
Max Act: 4.4160. Min Act: -0.1700
Data Index: 8433643 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #19