Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2256 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.9228. Min Range: -1.9228
Max Act: 1.9228. Min Act: -0.1643
Data Index: 6656329 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9228. Min Range: -1.9228
Max Act: 1.9142. Min Act: -0.1486
Data Index: 5909978 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9228. Min Range: -1.9228
Max Act: 1.9057. Min Act: -0.1530
Data Index: 3198979 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9228. Min Range: -1.9228
Max Act: 1.8887. Min Act: -0.1677
Data Index: 5125587 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9228. Min Range: -1.9228
Max Act: 1.8716. Min Act: -0.1671
Data Index: 8597658 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9228. Min Range: -1.9228
Max Act: 1.8630. Min Act: -0.1619
Data Index: 1946027 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9228. Min Range: -1.9228
Max Act: 1.8630. Min Act: -0.1575
Data Index: 999447 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9228. Min Range: -1.9228
Max Act: 1.8630. Min Act: -0.1700
Data Index: 6731880 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9228. Min Range: -1.9228
Max Act: 1.8545. Min Act: -0.1659
Data Index: 6601937 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9228. Min Range: -1.9228
Max Act: 1.8545. Min Act: -0.1646
Data Index: 141404 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9228. Min Range: -1.9228
Max Act: 1.8545. Min Act: -0.1543
Data Index: 3966638 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9228. Min Range: -1.9228
Max Act: 1.8545. Min Act: -0.1630
Data Index: 1050705 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9228. Min Range: -1.9228
Max Act: 1.8459. Min Act: -0.1437
Data Index: 2054476 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9228. Min Range: -1.9228
Max Act: 1.8459. Min Act: -0.1695
Data Index: 2344973 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9228. Min Range: -1.9228
Max Act: 1.8459. Min Act: -0.1630
Data Index: 8002880 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9228. Min Range: -1.9228
Max Act: 1.8459. Min Act: -0.1398
Data Index: 343789 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9228. Min Range: -1.9228
Max Act: 1.8545. Min Act: -0.1680
Data Index: 5434152 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9228. Min Range: -1.9228
Max Act: 1.8459. Min Act: -0.1413
Data Index: 7608518 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9228. Min Range: -1.9228
Max Act: 1.8373. Min Act: -0.1616
Data Index: 8319750 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9228. Min Range: -1.9228
Max Act: 1.8373. Min Act: -0.1668
Data Index: 4962867 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #19