Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4441 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.6991. Min Range: -9.6991
Max Act: 9.6991. Min Act: -0.1700
Data Index: 7457115 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.6991. Min Range: -9.6991
Max Act: 8.9491. Min Act: -0.1700
Data Index: 5502820 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.6991. Min Range: -9.6991
Max Act: 8.9491. Min Act: -0.1700
Data Index: 5933063 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.6991. Min Range: -9.6991
Max Act: 8.4491. Min Act: -0.1700
Data Index: 6768551 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.6991. Min Range: -9.6991
Max Act: 8.4491. Min Act: -0.1700
Data Index: 4697572 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.6991. Min Range: -9.6991
Max Act: 8.3241. Min Act: -0.1700
Data Index: 6274119 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.6991. Min Range: -9.6991
Max Act: 8.2616. Min Act: -0.1700
Data Index: 5735110 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.6991. Min Range: -9.6991
Max Act: 8.1366. Min Act: -0.1700
Data Index: 5596287 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.6991. Min Range: -9.6991
Max Act: 8.0741. Min Act: -0.1700
Data Index: 7291994 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.6991. Min Range: -9.6991
Max Act: 8.1366. Min Act: -0.1700
Data Index: 5405032 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.6991. Min Range: -9.6991
Max Act: 8.0741. Min Act: -0.1700
Data Index: 8637523 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.6991. Min Range: -9.6991
Max Act: 8.0741. Min Act: -0.1700
Data Index: 2327121 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.6991. Min Range: -9.6991
Max Act: 8.0741. Min Act: -0.1700
Data Index: 2733006 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.6991. Min Range: -9.6991
Max Act: 8.0116. Min Act: -0.1700
Data Index: 87593 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.6991. Min Range: -9.6991
Max Act: 8.0116. Min Act: -0.1700
Data Index: 2480146 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.6991. Min Range: -9.6991
Max Act: 8.0116. Min Act: -0.1700
Data Index: 8169367 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.6991. Min Range: -9.6991
Max Act: 8.0116. Min Act: -0.1700
Data Index: 4562511 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.6991. Min Range: -9.6991
Max Act: 8.0116. Min Act: -0.1700
Data Index: 1797468 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.6991. Min Range: -9.6991
Max Act: 8.0116. Min Act: -0.1700
Data Index: 2300021 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.6991. Min Range: -9.6991
Max Act: 8.0116. Min Act: -0.1700
Data Index: 1230727 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #19