Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6396 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3415. Min Range: -6.3415
Max Act: 6.3415. Min Act: -0.1700
Data Index: 8574567 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3415. Min Range: -6.3415
Max Act: 5.9977. Min Act: -0.1700
Data Index: 4608487 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3415. Min Range: -6.3415
Max Act: 5.9352. Min Act: -0.1700
Data Index: 3923952 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3415. Min Range: -6.3415
Max Act: 5.8727. Min Act: -0.1700
Data Index: 5397483 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3415. Min Range: -6.3415
Max Act: 5.8415. Min Act: -0.1700
Data Index: 3178804 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3415. Min Range: -6.3415
Max Act: 5.8415. Min Act: -0.1700
Data Index: 3686575 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3415. Min Range: -6.3415
Max Act: 5.8415. Min Act: -0.1700
Data Index: 2491142 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3415. Min Range: -6.3415
Max Act: 5.8102. Min Act: -0.1700
Data Index: 571679 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3415. Min Range: -6.3415
Max Act: 5.7790. Min Act: -0.1700
Data Index: 2220811 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3415. Min Range: -6.3415
Max Act: 5.7790. Min Act: -0.1700
Data Index: 661701 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3415. Min Range: -6.3415
Max Act: 5.7790. Min Act: -0.1700
Data Index: 1067888 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3415. Min Range: -6.3415
Max Act: 5.7790. Min Act: -0.1700
Data Index: 4394232 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3415. Min Range: -6.3415
Max Act: 5.7477. Min Act: -0.1700
Data Index: 2096375 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3415. Min Range: -6.3415
Max Act: 5.7165. Min Act: -0.1700
Data Index: 7620163 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3415. Min Range: -6.3415
Max Act: 5.7165. Min Act: -0.1700
Data Index: 3204518 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3415. Min Range: -6.3415
Max Act: 5.7165. Min Act: -0.1700
Data Index: 5712530 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3415. Min Range: -6.3415
Max Act: 5.7165. Min Act: -0.1700
Data Index: 4380889 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3415. Min Range: -6.3415
Max Act: 5.7165. Min Act: -0.1700
Data Index: 1710394 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3415. Min Range: -6.3415
Max Act: 5.7165. Min Act: -0.1700
Data Index: 6831120 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3415. Min Range: -6.3415
Max Act: 5.6540. Min Act: -0.1700
Data Index: 8591825 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #19