Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 645 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2328. Min Range: -6.2328
Max Act: 6.2328. Min Act: -0.1700
Data Index: 4839090 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2328. Min Range: -6.2328
Max Act: 6.2328. Min Act: -0.1700
Data Index: 3374267 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2328. Min Range: -6.2328
Max Act: 6.1078. Min Act: -0.1700
Data Index: 7580354 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2328. Min Range: -6.2328
Max Act: 6.0453. Min Act: -0.1700
Data Index: 7842566 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2328. Min Range: -6.2328
Max Act: 6.0453. Min Act: -0.1700
Data Index: 1503628 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2328. Min Range: -6.2328
Max Act: 6.1078. Min Act: -0.1700
Data Index: 4839088 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2328. Min Range: -6.2328
Max Act: 6.0453. Min Act: -0.1700
Data Index: 8235666 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2328. Min Range: -6.2328
Max Act: 6.0453. Min Act: -0.1700
Data Index: 7538486 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2328. Min Range: -6.2328
Max Act: 6.0453. Min Act: -0.1700
Data Index: 4839089 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2328. Min Range: -6.2328
Max Act: 6.0766. Min Act: -0.1700
Data Index: 6494549 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2328. Min Range: -6.2328
Max Act: 6.0141. Min Act: -0.1700
Data Index: 7580355 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2328. Min Range: -6.2328
Max Act: 5.9828. Min Act: -0.1700
Data Index: 1962781 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2328. Min Range: -6.2328
Max Act: 5.9828. Min Act: -0.1700
Data Index: 642380 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2328. Min Range: -6.2328
Max Act: 5.9828. Min Act: -0.1700
Data Index: 4406812 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2328. Min Range: -6.2328
Max Act: 5.9516. Min Act: -0.1700
Data Index: 6803 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2328. Min Range: -6.2328
Max Act: 5.9516. Min Act: -0.1700
Data Index: 3557137 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2328. Min Range: -6.2328
Max Act: 5.9828. Min Act: -0.1700
Data Index: 234258 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2328. Min Range: -6.2328
Max Act: 5.9516. Min Act: -0.1700
Data Index: 234247 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2328. Min Range: -6.2328
Max Act: 5.9203. Min Act: -0.1700
Data Index: 385497 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2328. Min Range: -6.2328
Max Act: 5.9203. Min Act: -0.1700
Data Index: 399501 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #19