Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1664 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1114. Min Range: -5.1114
Max Act: 5.1114. Min Act: -0.1700
Data Index: 1760275 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1114. Min Range: -5.1114
Max Act: 5.0176. Min Act: -0.1700
Data Index: 4545201 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1114. Min Range: -5.1114
Max Act: 4.9864. Min Act: -0.1700
Data Index: 6018889 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1114. Min Range: -5.1114
Max Act: 4.8614. Min Act: -0.1700
Data Index: 6195177 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1114. Min Range: -5.1114
Max Act: 4.8614. Min Act: -0.1700
Data Index: 544685 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1114. Min Range: -5.1114
Max Act: 4.7989. Min Act: -0.1700
Data Index: 3896694 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1114. Min Range: -5.1114
Max Act: 4.7364. Min Act: -0.1700
Data Index: 1627049 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1114. Min Range: -5.1114
Max Act: 4.7364. Min Act: -0.1700
Data Index: 5981580 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1114. Min Range: -5.1114
Max Act: 4.7364. Min Act: -0.1700
Data Index: 829596 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1114. Min Range: -5.1114
Max Act: 4.7051. Min Act: -0.1700
Data Index: 2934805 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1114. Min Range: -5.1114
Max Act: 4.7051. Min Act: -0.1700
Data Index: 3896710 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1114. Min Range: -5.1114
Max Act: 4.7051. Min Act: -0.1700
Data Index: 6115294 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1114. Min Range: -5.1114
Max Act: 4.6739. Min Act: -0.1700
Data Index: 7980085 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1114. Min Range: -5.1114
Max Act: 4.7051. Min Act: -0.1700
Data Index: 6115298 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1114. Min Range: -5.1114
Max Act: 4.6739. Min Act: -0.1700
Data Index: 3896718 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1114. Min Range: -5.1114
Max Act: 4.6739. Min Act: -0.1700
Data Index: 5361571 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1114. Min Range: -5.1114
Max Act: 4.6426. Min Act: -0.1700
Data Index: 4329335 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1114. Min Range: -5.1114
Max Act: 4.6739. Min Act: -0.1700
Data Index: 3896719 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1114. Min Range: -5.1114
Max Act: 4.6426. Min Act: -0.1700
Data Index: 3896699 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1114. Min Range: -5.1114
Max Act: 4.6426. Min Act: -0.1700
Data Index: 3896697 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #19