Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2908 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.7597. Min Range: -5.7597
Max Act: 5.7597. Min Act: -0.1700
Data Index: 1260103 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7597. Min Range: -5.7597
Max Act: 5.6347. Min Act: -0.1700
Data Index: 2502936 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7597. Min Range: -5.7597
Max Act: 5.5722. Min Act: -0.1700
Data Index: 4436904 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7597. Min Range: -5.7597
Max Act: 5.5410. Min Act: -0.1700
Data Index: 3918444 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7597. Min Range: -5.7597
Max Act: 5.5722. Min Act: -0.1700
Data Index: 7873629 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7597. Min Range: -5.7597
Max Act: 5.5097. Min Act: -0.1700
Data Index: 4769133 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7597. Min Range: -5.7597
Max Act: 5.4785. Min Act: -0.1700
Data Index: 256648 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7597. Min Range: -5.7597
Max Act: 5.4785. Min Act: -0.1700
Data Index: 3274955 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7597. Min Range: -5.7597
Max Act: 5.4785. Min Act: -0.1700
Data Index: 6906661 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7597. Min Range: -5.7597
Max Act: 5.4160. Min Act: -0.1700
Data Index: 2791778 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7597. Min Range: -5.7597
Max Act: 5.4472. Min Act: -0.1700
Data Index: 4793322 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7597. Min Range: -5.7597
Max Act: 5.4472. Min Act: -0.1700
Data Index: 5785146 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7597. Min Range: -5.7597
Max Act: 5.4472. Min Act: -0.1700
Data Index: 3721688 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7597. Min Range: -5.7597
Max Act: 5.4160. Min Act: -0.1700
Data Index: 4238981 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7597. Min Range: -5.7597
Max Act: 5.3847. Min Act: -0.1700
Data Index: 6877954 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7597. Min Range: -5.7597
Max Act: 5.4160. Min Act: -0.1700
Data Index: 5512160 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7597. Min Range: -5.7597
Max Act: 5.3847. Min Act: -0.1700
Data Index: 8263664 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7597. Min Range: -5.7597
Max Act: 5.3847. Min Act: -0.1700
Data Index: 8055190 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7597. Min Range: -5.7597
Max Act: 5.3847. Min Act: -0.1700
Data Index: 5895427 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7597. Min Range: -5.7597
Max Act: 5.3847. Min Act: -0.1700
Data Index: 6011338 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #19