Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 444 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9847. Min Range: -3.9847
Max Act: 3.9847. Min Act: -0.1700
Data Index: 872920 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9847. Min Range: -3.9847
Max Act: 3.9534. Min Act: -0.1700
Data Index: 6031097 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9847. Min Range: -3.9847
Max Act: 3.8909. Min Act: -0.1700
Data Index: 1717137 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9847. Min Range: -3.9847
Max Act: 3.8909. Min Act: -0.1700
Data Index: 7474539 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9847. Min Range: -3.9847
Max Act: 3.9222. Min Act: -0.1700
Data Index: 5643964 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9847. Min Range: -3.9847
Max Act: 3.8596. Min Act: -0.1700
Data Index: 1767 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9847. Min Range: -3.9847
Max Act: 3.8596. Min Act: -0.1700
Data Index: 5155471 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9847. Min Range: -3.9847
Max Act: 3.8283. Min Act: -0.1700
Data Index: 1100954 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9847. Min Range: -3.9847
Max Act: 3.8283. Min Act: -0.1700
Data Index: 1457656 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9847. Min Range: -3.9847
Max Act: 3.7971. Min Act: -0.1700
Data Index: 7829176 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9847. Min Range: -3.9847
Max Act: 3.7971. Min Act: -0.1700
Data Index: 7816081 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9847. Min Range: -3.9847
Max Act: 3.7658. Min Act: -0.1700
Data Index: 570495 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9847. Min Range: -3.9847
Max Act: 3.7971. Min Act: -0.1700
Data Index: 3808067 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9847. Min Range: -3.9847
Max Act: 3.7971. Min Act: -0.1700
Data Index: 209112 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9847. Min Range: -3.9847
Max Act: 3.7345. Min Act: -0.1700
Data Index: 2981699 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9847. Min Range: -3.9847
Max Act: 3.7658. Min Act: -0.1700
Data Index: 4412477 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9847. Min Range: -3.9847
Max Act: 3.7658. Min Act: -0.1700
Data Index: 5945608 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9847. Min Range: -3.9847
Max Act: 3.7658. Min Act: -0.1700
Data Index: 3242130 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9847. Min Range: -3.9847
Max Act: 3.7658. Min Act: -0.1700
Data Index: 606841 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9847. Min Range: -3.9847
Max Act: 3.7658. Min Act: -0.1700
Data Index: 6945425 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #19