Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6154 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.1421. Min Range: -2.1421
Max Act: 2.1421. Min Act: -0.1700
Data Index: 7963576 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1421. Min Range: -2.1421
Max Act: 2.1254. Min Act: -0.1700
Data Index: 2056261 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1421. Min Range: -2.1421
Max Act: 2.1254. Min Act: -0.1700
Data Index: 6574779 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1421. Min Range: -2.1421
Max Act: 2.1087. Min Act: -0.1700
Data Index: 638470 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1421. Min Range: -2.1421
Max Act: 2.0920. Min Act: -0.1700
Data Index: 4026518 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1421. Min Range: -2.1421
Max Act: 2.0920. Min Act: -0.1700
Data Index: 7473688 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1421. Min Range: -2.1421
Max Act: 2.0752. Min Act: -0.1700
Data Index: 1997637 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1421. Min Range: -2.1421
Max Act: 2.0752. Min Act: -0.1700
Data Index: 590094 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1421. Min Range: -2.1421
Max Act: 2.0752. Min Act: -0.1700
Data Index: 4807772 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1421. Min Range: -2.1421
Max Act: 2.0752. Min Act: -0.1700
Data Index: 2247748 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1421. Min Range: -2.1421
Max Act: 2.0584. Min Act: -0.1700
Data Index: 5108177 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1421. Min Range: -2.1421
Max Act: 2.0584. Min Act: -0.1700
Data Index: 4286249 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1421. Min Range: -2.1421
Max Act: 2.0584. Min Act: -0.1700
Data Index: 696330 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1421. Min Range: -2.1421
Max Act: 2.0584. Min Act: -0.1700
Data Index: 8732467 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1421. Min Range: -2.1421
Max Act: 2.0584. Min Act: -0.1700
Data Index: 250697 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1421. Min Range: -2.1421
Max Act: 2.0584. Min Act: -0.1700
Data Index: 3472268 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1421. Min Range: -2.1421
Max Act: 2.0584. Min Act: -0.1700
Data Index: 3289047 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1421. Min Range: -2.1421
Max Act: 2.0584. Min Act: -0.1700
Data Index: 951018 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1421. Min Range: -2.1421
Max Act: 2.0416. Min Act: -0.1700
Data Index: 4965006 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1421. Min Range: -2.1421
Max Act: 2.0416. Min Act: -0.1700
Data Index: 4561028 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #19