Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2495 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.5368. Min Range: -4.5368
Max Act: 4.5368. Min Act: -0.1700
Data Index: 7064712 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5368. Min Range: -4.5368
Max Act: 4.3493. Min Act: -0.1700
Data Index: 3637428 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5368. Min Range: -4.5368
Max Act: 4.3493. Min Act: -0.1700
Data Index: 1470902 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5368. Min Range: -4.5368
Max Act: 4.3493. Min Act: -0.1700
Data Index: 7906029 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5368. Min Range: -4.5368
Max Act: 4.3493. Min Act: -0.1700
Data Index: 8260844 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5368. Min Range: -4.5368
Max Act: 4.3493. Min Act: -0.1700
Data Index: 5273845 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5368. Min Range: -4.5368
Max Act: 4.3493. Min Act: -0.1700
Data Index: 2727585 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5368. Min Range: -4.5368
Max Act: 4.3493. Min Act: -0.1700
Data Index: 3870858 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5368. Min Range: -4.5368
Max Act: 4.3493. Min Act: -0.1700
Data Index: 642138 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5368. Min Range: -4.5368
Max Act: 4.3493. Min Act: -0.1700
Data Index: 6118348 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5368. Min Range: -4.5368
Max Act: 4.3493. Min Act: -0.1700
Data Index: 7959505 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5368. Min Range: -4.5368
Max Act: 4.3493. Min Act: -0.1700
Data Index: 715203 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5368. Min Range: -4.5368
Max Act: 4.3493. Min Act: -0.1700
Data Index: 1803619 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5368. Min Range: -4.5368
Max Act: 4.3493. Min Act: -0.1700
Data Index: 6830800 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5368. Min Range: -4.5368
Max Act: 4.3493. Min Act: -0.1700
Data Index: 5386646 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5368. Min Range: -4.5368
Max Act: 4.3181. Min Act: -0.1700
Data Index: 2780972 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5368. Min Range: -4.5368
Max Act: 4.2868. Min Act: -0.1700
Data Index: 8537734 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5368. Min Range: -4.5368
Max Act: 4.2243. Min Act: -0.1700
Data Index: 5415375 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5368. Min Range: -4.5368
Max Act: 4.1931. Min Act: -0.1700
Data Index: 3331759 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5368. Min Range: -4.5368
Max Act: 4.1931. Min Act: -0.1700
Data Index: 1341164 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19