Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4259 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9227. Min Range: -7.9227
Max Act: 7.9227. Min Act: -0.1700
Data Index: 7824935 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9227. Min Range: -7.9227
Max Act: 7.7352. Min Act: -0.1700
Data Index: 5454868 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9227. Min Range: -7.9227
Max Act: 7.7352. Min Act: -0.1700
Data Index: 4265034 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9227. Min Range: -7.9227
Max Act: 7.7352. Min Act: -0.1700
Data Index: 789612 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9227. Min Range: -7.9227
Max Act: 7.5789. Min Act: -0.1700
Data Index: 1739937 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9227. Min Range: -7.9227
Max Act: 7.4539. Min Act: -0.1700
Data Index: 5477250 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9227. Min Range: -7.9227
Max Act: 7.3289. Min Act: -0.1700
Data Index: 4011153 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9227. Min Range: -7.9227
Max Act: 7.3289. Min Act: -0.1700
Data Index: 6844568 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9227. Min Range: -7.9227
Max Act: 7.2664. Min Act: -0.1700
Data Index: 3489511 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9227. Min Range: -7.9227
Max Act: 7.2977. Min Act: -0.1700
Data Index: 1766089 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9227. Min Range: -7.9227
Max Act: 7.2352. Min Act: -0.1700
Data Index: 8011936 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9227. Min Range: -7.9227
Max Act: 7.2352. Min Act: -0.1700
Data Index: 2705272 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9227. Min Range: -7.9227
Max Act: 7.2664. Min Act: -0.1700
Data Index: 2054287 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9227. Min Range: -7.9227
Max Act: 7.2352. Min Act: -0.1700
Data Index: 8818036 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9227. Min Range: -7.9227
Max Act: 7.2039. Min Act: -0.1700
Data Index: 1506129 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9227. Min Range: -7.9227
Max Act: 7.1727. Min Act: -0.1700
Data Index: 7224348 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9227. Min Range: -7.9227
Max Act: 7.1727. Min Act: -0.1700
Data Index: 7480464 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9227. Min Range: -7.9227
Max Act: 7.1727. Min Act: -0.1700
Data Index: 3847596 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9227. Min Range: -7.9227
Max Act: 7.1727. Min Act: -0.1700
Data Index: 487162 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9227. Min Range: -7.9227
Max Act: 7.1727. Min Act: -0.1700
Data Index: 4742726 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #19