Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3633 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9067. Min Range: -4.9067
Max Act: 4.9067. Min Act: -0.1700
Data Index: 6687381 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9067. Min Range: -4.9067
Max Act: 4.9067. Min Act: -0.1700
Data Index: 5568152 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9067. Min Range: -4.9067
Max Act: 4.8130. Min Act: -0.1700
Data Index: 1707017 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9067. Min Range: -4.9067
Max Act: 4.8130. Min Act: -0.1700
Data Index: 1495251 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9067. Min Range: -4.9067
Max Act: 4.8130. Min Act: -0.1700
Data Index: 1177519 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9067. Min Range: -4.9067
Max Act: 4.8130. Min Act: -0.1700
Data Index: 6334739 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9067. Min Range: -4.9067
Max Act: 4.7505. Min Act: -0.1700
Data Index: 869074 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9067. Min Range: -4.9067
Max Act: 4.7505. Min Act: -0.1700
Data Index: 4007746 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9067. Min Range: -4.9067
Max Act: 4.6880. Min Act: -0.1700
Data Index: 4225889 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9067. Min Range: -4.9067
Max Act: 4.7505. Min Act: -0.1700
Data Index: 3634007 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9067. Min Range: -4.9067
Max Act: 4.6880. Min Act: -0.1700
Data Index: 6620085 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9067. Min Range: -4.9067
Max Act: 4.7505. Min Act: -0.1700
Data Index: 144317 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9067. Min Range: -4.9067
Max Act: 4.7192. Min Act: -0.1700
Data Index: 1055658 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9067. Min Range: -4.9067
Max Act: 4.7192. Min Act: -0.1700
Data Index: 979960 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9067. Min Range: -4.9067
Max Act: 4.7192. Min Act: -0.1700
Data Index: 1450395 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9067. Min Range: -4.9067
Max Act: 4.6880. Min Act: -0.1700
Data Index: 2616092 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9067. Min Range: -4.9067
Max Act: 4.6880. Min Act: -0.1700
Data Index: 2712162 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9067. Min Range: -4.9067
Max Act: 4.6880. Min Act: -0.1700
Data Index: 2156234 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9067. Min Range: -4.9067
Max Act: 4.6255. Min Act: -0.1700
Data Index: 1737008 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9067. Min Range: -4.9067
Max Act: 4.6567. Min Act: -0.1700
Data Index: 666166 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #19