Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1615 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.3078. Min Range: -4.3078
Max Act: 4.3078. Min Act: -0.1700
Data Index: 4802244 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3078. Min Range: -4.3078
Max Act: 4.3078. Min Act: -0.1700
Data Index: 935012 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3078. Min Range: -4.3078
Max Act: 4.2765. Min Act: -0.1700
Data Index: 7412194 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3078. Min Range: -4.3078
Max Act: 4.2765. Min Act: -0.1700
Data Index: 2024654 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3078. Min Range: -4.3078
Max Act: 4.2765. Min Act: -0.1700
Data Index: 538174 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3078. Min Range: -4.3078
Max Act: 4.2453. Min Act: -0.1699
Data Index: 8181602 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3078. Min Range: -4.3078
Max Act: 4.2453. Min Act: -0.1700
Data Index: 6217024 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3078. Min Range: -4.3078
Max Act: 4.2140. Min Act: -0.1700
Data Index: 4500251 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3078. Min Range: -4.3078
Max Act: 4.2140. Min Act: -0.1700
Data Index: 2091705 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3078. Min Range: -4.3078
Max Act: 4.2140. Min Act: -0.1700
Data Index: 1928852 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3078. Min Range: -4.3078
Max Act: 4.1828. Min Act: -0.1700
Data Index: 8283900 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3078. Min Range: -4.3078
Max Act: 4.2140. Min Act: -0.1700
Data Index: 4502914 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3078. Min Range: -4.3078
Max Act: 4.2140. Min Act: -0.1700
Data Index: 8047179 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3078. Min Range: -4.3078
Max Act: 4.2140. Min Act: -0.1700
Data Index: 4055283 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3078. Min Range: -4.3078
Max Act: 4.1828. Min Act: -0.1700
Data Index: 7509131 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3078. Min Range: -4.3078
Max Act: 4.2140. Min Act: -0.1700
Data Index: 3010281 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3078. Min Range: -4.3078
Max Act: 4.2140. Min Act: -0.1700
Data Index: 7227508 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3078. Min Range: -4.3078
Max Act: 4.2140. Min Act: -0.1700
Data Index: 2593709 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3078. Min Range: -4.3078
Max Act: 4.1828. Min Act: -0.1700
Data Index: 4579187 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3078. Min Range: -4.3078
Max Act: 4.1828. Min Act: -0.1700
Data Index: 4666515 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #19