Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 869 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.2116. Min Range: -5.2116
Max Act: 5.2116. Min Act: -0.1700
Data Index: 8672296 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2116. Min Range: -5.2116
Max Act: 4.8366. Min Act: -0.1700
Data Index: 4895598 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2116. Min Range: -5.2116
Max Act: 4.7741. Min Act: -0.1700
Data Index: 4487919 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2116. Min Range: -5.2116
Max Act: 4.7429. Min Act: -0.1700
Data Index: 7485872 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2116. Min Range: -5.2116
Max Act: 4.7429. Min Act: -0.1700
Data Index: 8754058 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2116. Min Range: -5.2116
Max Act: 4.7116. Min Act: -0.1700
Data Index: 3462335 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2116. Min Range: -5.2116
Max Act: 4.6804. Min Act: -0.1700
Data Index: 4217448 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2116. Min Range: -5.2116
Max Act: 4.6491. Min Act: -0.1700
Data Index: 2709543 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2116. Min Range: -5.2116
Max Act: 4.6804. Min Act: -0.1700
Data Index: 5859300 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2116. Min Range: -5.2116
Max Act: 4.6804. Min Act: -0.1700
Data Index: 1993788 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2116. Min Range: -5.2116
Max Act: 4.6804. Min Act: -0.1700
Data Index: 3983831 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2116. Min Range: -5.2116
Max Act: 4.6491. Min Act: -0.1686
Data Index: 4560446 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2116. Min Range: -5.2116
Max Act: 4.6491. Min Act: -0.1700
Data Index: 3088746 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2116. Min Range: -5.2116
Max Act: 4.6491. Min Act: -0.1700
Data Index: 7269224 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2116. Min Range: -5.2116
Max Act: 4.6491. Min Act: -0.1699
Data Index: 2709544 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2116. Min Range: -5.2116
Max Act: 4.6178. Min Act: -0.1700
Data Index: 2055965 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2116. Min Range: -5.2116
Max Act: 4.6178. Min Act: -0.1700
Data Index: 3088751 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2116. Min Range: -5.2116
Max Act: 4.6178. Min Act: -0.1700
Data Index: 229224 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2116. Min Range: -5.2116
Max Act: 4.6178. Min Act: -0.1700
Data Index: 4942503 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2116. Min Range: -5.2116
Max Act: 4.6178. Min Act: -0.1700
Data Index: 5743640 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19