Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5101 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.5616. Min Range: -2.5616
Max Act: 2.5616. Min Act: -0.1424
Data Index: 4650085 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5616. Min Range: -2.5616
Max Act: 2.4483. Min Act: -0.1696
Data Index: 8041994 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5616. Min Range: -2.5616
Max Act: 2.4483. Min Act: -0.1700
Data Index: 1495143 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5616. Min Range: -2.5616
Max Act: 2.4320. Min Act: -0.1700
Data Index: 1051227 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5616. Min Range: -2.5616
Max Act: 2.4157. Min Act: -0.1700
Data Index: 2800808 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5616. Min Range: -2.5616
Max Act: 2.4157. Min Act: -0.1687
Data Index: 4617699 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5616. Min Range: -2.5616
Max Act: 2.3831. Min Act: -0.1700
Data Index: 7927855 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5616. Min Range: -2.5616
Max Act: 2.3994. Min Act: -0.1697
Data Index: 7849768 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5616. Min Range: -2.5616
Max Act: 2.3994. Min Act: -0.1700
Data Index: 4915599 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5616. Min Range: -2.5616
Max Act: 2.3994. Min Act: -0.1696
Data Index: 5844741 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5616. Min Range: -2.5616
Max Act: 2.3831. Min Act: -0.1700
Data Index: 3759261 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5616. Min Range: -2.5616
Max Act: 2.3503. Min Act: -0.1692
Data Index: 1449388 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5616. Min Range: -2.5616
Max Act: 2.3667. Min Act: -0.1700
Data Index: 3534001 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5616. Min Range: -2.5616
Max Act: 2.3667. Min Act: -0.1685
Data Index: 7810770 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5616. Min Range: -2.5616
Max Act: 2.3667. Min Act: -0.1678
Data Index: 2662345 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5616. Min Range: -2.5616
Max Act: 2.3503. Min Act: -0.1689
Data Index: 6479109 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5616. Min Range: -2.5616
Max Act: 2.3503. Min Act: -0.1700
Data Index: 1349815 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5616. Min Range: -2.5616
Max Act: 2.3503. Min Act: -0.1700
Data Index: 946198 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5616. Min Range: -2.5616
Max Act: 2.3503. Min Act: -0.1699
Data Index: 2542856 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5616. Min Range: -2.5616
Max Act: 2.3503. Min Act: -0.1700
Data Index: 3979861 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #19