Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2985 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8432. Min Range: -3.8432
Max Act: 3.8432. Min Act: -0.1700
Data Index: 2194765 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8432. Min Range: -3.8432
Max Act: 3.7807. Min Act: -0.1700
Data Index: 3152928 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8432. Min Range: -3.8432
Max Act: 3.7494. Min Act: -0.1700
Data Index: 4737600 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8432. Min Range: -3.8432
Max Act: 3.7181. Min Act: -0.1700
Data Index: 1049759 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8432. Min Range: -3.8432
Max Act: 3.7181. Min Act: -0.1700
Data Index: 4548355 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8432. Min Range: -3.8432
Max Act: 3.7181. Min Act: -0.1700
Data Index: 6269605 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8432. Min Range: -3.8432
Max Act: 3.6868. Min Act: -0.1700
Data Index: 4553961 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8432. Min Range: -3.8432
Max Act: 3.6868. Min Act: -0.1700
Data Index: 25773 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8432. Min Range: -3.8432
Max Act: 3.6868. Min Act: -0.1700
Data Index: 2508611 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8432. Min Range: -3.8432
Max Act: 3.7181. Min Act: -0.1700
Data Index: 8641208 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8432. Min Range: -3.8432
Max Act: 3.6555. Min Act: -0.1700
Data Index: 3658976 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8432. Min Range: -3.8432
Max Act: 3.6555. Min Act: -0.1700
Data Index: 7268833 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8432. Min Range: -3.8432
Max Act: 3.6555. Min Act: -0.1700
Data Index: 5998208 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8432. Min Range: -3.8432
Max Act: 3.6242. Min Act: -0.1700
Data Index: 8627189 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8432. Min Range: -3.8432
Max Act: 3.6242. Min Act: -0.1700
Data Index: 5759085 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8432. Min Range: -3.8432
Max Act: 3.6242. Min Act: -0.1700
Data Index: 5352317 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8432. Min Range: -3.8432
Max Act: 3.6242. Min Act: -0.1700
Data Index: 6147768 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8432. Min Range: -3.8432
Max Act: 3.6242. Min Act: -0.1700
Data Index: 4975786 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8432. Min Range: -3.8432
Max Act: 3.6555. Min Act: -0.1700
Data Index: 4552424 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8432. Min Range: -3.8432
Max Act: 3.5929. Min Act: -0.1700
Data Index: 1383958 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #19