Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3889 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5879. Min Range: -6.5879
Max Act: 6.5879. Min Act: -0.1700
Data Index: 5336891 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5879. Min Range: -6.5879
Max Act: 6.4942. Min Act: -0.1700
Data Index: 561300 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5879. Min Range: -6.5879
Max Act: 6.4004. Min Act: -0.1700
Data Index: 1826616 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5879. Min Range: -6.5879
Max Act: 6.3379. Min Act: -0.1700
Data Index: 6016862 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5879. Min Range: -6.5879
Max Act: 6.3692. Min Act: -0.1700
Data Index: 1264317 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5879. Min Range: -6.5879
Max Act: 6.3067. Min Act: -0.1700
Data Index: 2595067 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5879. Min Range: -6.5879
Max Act: 6.2129. Min Act: -0.1700
Data Index: 8409472 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5879. Min Range: -6.5879
Max Act: 6.2129. Min Act: -0.1700
Data Index: 2361520 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5879. Min Range: -6.5879
Max Act: 6.2129. Min Act: -0.1700
Data Index: 5422595 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5879. Min Range: -6.5879
Max Act: 6.2129. Min Act: -0.1700
Data Index: 3894171 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5879. Min Range: -6.5879
Max Act: 6.1817. Min Act: -0.1700
Data Index: 7574162 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5879. Min Range: -6.5879
Max Act: 6.1817. Min Act: -0.1700
Data Index: 3790343 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5879. Min Range: -6.5879
Max Act: 6.1504. Min Act: -0.1700
Data Index: 4266387 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5879. Min Range: -6.5879
Max Act: 6.1504. Min Act: -0.1700
Data Index: 7682839 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5879. Min Range: -6.5879
Max Act: 6.1504. Min Act: -0.1700
Data Index: 2562476 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5879. Min Range: -6.5879
Max Act: 6.1504. Min Act: -0.1700
Data Index: 2265935 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5879. Min Range: -6.5879
Max Act: 6.1504. Min Act: -0.1700
Data Index: 735252 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5879. Min Range: -6.5879
Max Act: 6.1192. Min Act: -0.1700
Data Index: 2117475 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5879. Min Range: -6.5879
Max Act: 6.1192. Min Act: -0.1700
Data Index: 248991 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5879. Min Range: -6.5879
Max Act: 6.0879. Min Act: -0.1700
Data Index: 2801043 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #19