Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4443 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.7505. Min Range: -5.7505
Max Act: 5.7505. Min Act: -0.1700
Data Index: 8406703 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7505. Min Range: -5.7505
Max Act: 5.7193. Min Act: -0.1700
Data Index: 2440154 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7505. Min Range: -5.7505
Max Act: 5.5318. Min Act: -0.1700
Data Index: 1139626 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7505. Min Range: -5.7505
Max Act: 5.4068. Min Act: -0.1700
Data Index: 2762086 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7505. Min Range: -5.7505
Max Act: 5.3130. Min Act: -0.1700
Data Index: 6330941 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7505. Min Range: -5.7505
Max Act: 5.3130. Min Act: -0.1700
Data Index: 8006907 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7505. Min Range: -5.7505
Max Act: 5.1880. Min Act: -0.1700
Data Index: 3719994 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7505. Min Range: -5.7505
Max Act: 5.1568. Min Act: -0.1700
Data Index: 5500779 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7505. Min Range: -5.7505
Max Act: 5.1568. Min Act: -0.1700
Data Index: 5688417 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7505. Min Range: -5.7505
Max Act: 5.0943. Min Act: -0.1700
Data Index: 8545844 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7505. Min Range: -5.7505
Max Act: 5.0943. Min Act: -0.1700
Data Index: 5334549 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7505. Min Range: -5.7505
Max Act: 5.0943. Min Act: -0.1700
Data Index: 5334541 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7505. Min Range: -5.7505
Max Act: 5.0630. Min Act: -0.1700
Data Index: 2109898 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7505. Min Range: -5.7505
Max Act: 5.0318. Min Act: -0.1700
Data Index: 8263119 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7505. Min Range: -5.7505
Max Act: 5.0318. Min Act: -0.1700
Data Index: 2710539 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7505. Min Range: -5.7505
Max Act: 5.0005. Min Act: -0.1700
Data Index: 2762085 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7505. Min Range: -5.7505
Max Act: 5.0005. Min Act: -0.1700
Data Index: 8006906 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7505. Min Range: -5.7505
Max Act: 5.0005. Min Act: -0.1700
Data Index: 2085424 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7505. Min Range: -5.7505
Max Act: 4.9693. Min Act: -0.1700
Data Index: 8006904 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7505. Min Range: -5.7505
Max Act: 4.9693. Min Act: -0.1700
Data Index: 8006905 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #19