Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4676 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.2370. Min Range: -3.2370
Max Act: 3.2370. Min Act: -0.1700
Data Index: 5330585 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2370. Min Range: -3.2370
Max Act: 3.1583. Min Act: -0.1700
Data Index: 8778821 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2370. Min Range: -3.2370
Max Act: 3.1111. Min Act: -0.1700
Data Index: 901098 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2370. Min Range: -3.2370
Max Act: 3.0953. Min Act: -0.1700
Data Index: 1966405 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2370. Min Range: -3.2370
Max Act: 3.0638. Min Act: -0.1700
Data Index: 1692617 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2370. Min Range: -3.2370
Max Act: 3.0480. Min Act: -0.1700
Data Index: 8560464 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2370. Min Range: -3.2370
Max Act: 3.0638. Min Act: -0.1700
Data Index: 3016260 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2370. Min Range: -3.2370
Max Act: 3.0480. Min Act: -0.1700
Data Index: 7404816 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2370. Min Range: -3.2370
Max Act: 3.0322. Min Act: -0.1700
Data Index: 6908431 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2370. Min Range: -3.2370
Max Act: 3.0322. Min Act: -0.1700
Data Index: 4778215 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2370. Min Range: -3.2370
Max Act: 3.0164. Min Act: -0.1700
Data Index: 6210586 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2370. Min Range: -3.2370
Max Act: 3.0006. Min Act: -0.1700
Data Index: 2556559 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2370. Min Range: -3.2370
Max Act: 3.0006. Min Act: -0.1700
Data Index: 8684112 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2370. Min Range: -3.2370
Max Act: 2.9848. Min Act: -0.1700
Data Index: 6827902 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2370. Min Range: -3.2370
Max Act: 3.0006. Min Act: -0.1700
Data Index: 4652461 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2370. Min Range: -3.2370
Max Act: 2.9848. Min Act: -0.1700
Data Index: 369129 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2370. Min Range: -3.2370
Max Act: 2.9848. Min Act: -0.1700
Data Index: 2575908 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2370. Min Range: -3.2370
Max Act: 2.9690. Min Act: -0.1700
Data Index: 173721 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2370. Min Range: -3.2370
Max Act: 2.9532. Min Act: -0.1700
Data Index: 1480085 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2370. Min Range: -3.2370
Max Act: 2.9532. Min Act: -0.1700
Data Index: 6594137 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #19