Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3095 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3699. Min Range: -8.3699
Max Act: 8.3699. Min Act: -0.1700
Data Index: 5079362 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3699. Min Range: -8.3699
Max Act: 8.3074. Min Act: -0.1700
Data Index: 2763615 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3699. Min Range: -8.3699
Max Act: 8.1824. Min Act: -0.1700
Data Index: 1394583 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3699. Min Range: -8.3699
Max Act: 8.1199. Min Act: -0.1700
Data Index: 888602 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3699. Min Range: -8.3699
Max Act: 8.1199. Min Act: -0.1700
Data Index: 7392290 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3699. Min Range: -8.3699
Max Act: 8.0574. Min Act: -0.1700
Data Index: 7536850 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3699. Min Range: -8.3699
Max Act: 8.1199. Min Act: -0.1700
Data Index: 2118007 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3699. Min Range: -8.3699
Max Act: 8.0574. Min Act: -0.1700
Data Index: 8469299 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3699. Min Range: -8.3699
Max Act: 8.1199. Min Act: -0.1700
Data Index: 390666 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3699. Min Range: -8.3699
Max Act: 8.1199. Min Act: -0.1700
Data Index: 8168371 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3699. Min Range: -8.3699
Max Act: 8.1199. Min Act: -0.1700
Data Index: 7999793 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3699. Min Range: -8.3699
Max Act: 8.0574. Min Act: -0.1700
Data Index: 1864157 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3699. Min Range: -8.3699
Max Act: 8.0574. Min Act: -0.1700
Data Index: 160153 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3699. Min Range: -8.3699
Max Act: 8.1199. Min Act: -0.1700
Data Index: 1830684 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3699. Min Range: -8.3699
Max Act: 8.0574. Min Act: -0.1700
Data Index: 4856041 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3699. Min Range: -8.3699
Max Act: 8.1199. Min Act: -0.1700
Data Index: 475549 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3699. Min Range: -8.3699
Max Act: 8.0574. Min Act: -0.1700
Data Index: 7287505 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3699. Min Range: -8.3699
Max Act: 8.1199. Min Act: -0.1700
Data Index: 6402994 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3699. Min Range: -8.3699
Max Act: 8.0574. Min Act: -0.1700
Data Index: 998588 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3699. Min Range: -8.3699
Max Act: 8.0574. Min Act: -0.1700
Data Index: 1996846 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #19