Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3874 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 0.5322. Min Range: -0.5322
Max Act: 0.5322. Min Act: -0.1694
Data Index: 8376262 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.5322. Min Range: -0.5322
Max Act: 0.4795. Min Act: -0.1686
Data Index: 4750372 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.5322. Min Range: -0.5322
Max Act: 0.4795. Min Act: -0.1699
Data Index: 5534763 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.5322. Min Range: -0.5322
Max Act: 0.4795. Min Act: -0.1687
Data Index: 1768446 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.5322. Min Range: -0.5322
Max Act: 0.4795. Min Act: -0.1699
Data Index: 8416321 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.5322. Min Range: -0.5322
Max Act: 0.4795. Min Act: -0.1700
Data Index: 2559139 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.5322. Min Range: -0.5322
Max Act: 0.4795. Min Act: -0.1653
Data Index: 5409140 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.5322. Min Range: -0.5322
Max Act: 0.4795. Min Act: -0.1683
Data Index: 2210967 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.5322. Min Range: -0.5322
Max Act: 0.4068. Min Act: -0.1700
Data Index: 1298426 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.5322. Min Range: -0.5322
Max Act: 0.4068. Min Act: -0.1700
Data Index: 7406619 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.5322. Min Range: -0.5322
Max Act: 0.3927. Min Act: -0.1622
Data Index: 6813016 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.5322. Min Range: -0.5322
Max Act: 0.3857. Min Act: -0.1700
Data Index: 7550119 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.5322. Min Range: -0.5322
Max Act: 0.3927. Min Act: -0.1592
Data Index: 1598341 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.5322. Min Range: -0.5322
Max Act: 0.3857. Min Act: -0.1694
Data Index: 6393522 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.5322. Min Range: -0.5322
Max Act: 0.3787. Min Act: -0.1694
Data Index: 3554072 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.5322. Min Range: -0.5322
Max Act: 0.3857. Min Act: -0.1698
Data Index: 8324700 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.5322. Min Range: -0.5322
Max Act: 0.3787. Min Act: -0.1686
Data Index: 1258367 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.5322. Min Range: -0.5322
Max Act: 0.3787. Min Act: -0.1700
Data Index: 7166604 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.5322. Min Range: -0.5322
Max Act: 0.3718. Min Act: -0.1694
Data Index: 2962807 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.5322. Min Range: -0.5322
Max Act: 0.3787. Min Act: -0.1700
Data Index: 463341 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #19