Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2687 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 16.6527. Min Range: -16.6527
Max Act: 16.6527. Min Act: -0.1700
Data Index: 2956096 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 16.6527. Min Range: -16.6527
Max Act: 16.5277. Min Act: -0.1700
Data Index: 801179 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 16.6527. Min Range: -16.6527
Max Act: 16.4027. Min Act: -0.1700
Data Index: 2956098 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 16.6527. Min Range: -16.6527
Max Act: 16.2777. Min Act: -0.1700
Data Index: 2956097 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 16.6527. Min Range: -16.6527
Max Act: 16.0277. Min Act: -0.1700
Data Index: 6510724 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 16.6527. Min Range: -16.6527
Max Act: 15.9027. Min Act: -0.1700
Data Index: 1257138 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 16.6527. Min Range: -16.6527
Max Act: 15.9027. Min Act: -0.1700
Data Index: 2956099 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 16.6527. Min Range: -16.6527
Max Act: 15.8402. Min Act: -0.1700
Data Index: 2000412 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 16.6527. Min Range: -16.6527
Max Act: 15.5902. Min Act: -0.1700
Data Index: 3904505 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 16.6527. Min Range: -16.6527
Max Act: 15.5277. Min Act: -0.1700
Data Index: 1233129 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 16.6527. Min Range: -16.6527
Max Act: 15.5902. Min Act: -0.1700
Data Index: 7087765 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 16.6527. Min Range: -16.6527
Max Act: 15.4652. Min Act: -0.1700
Data Index: 4790492 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 16.6527. Min Range: -16.6527
Max Act: 15.4652. Min Act: -0.1700
Data Index: 1117156 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 16.6527. Min Range: -16.6527
Max Act: 15.4652. Min Act: -0.1700
Data Index: 1006497 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 16.6527. Min Range: -16.6527
Max Act: 15.3402. Min Act: -0.1700
Data Index: 3436770 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 16.6527. Min Range: -16.6527
Max Act: 15.3402. Min Act: -0.1700
Data Index: 829831 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 16.6527. Min Range: -16.6527
Max Act: 15.2152. Min Act: -0.1700
Data Index: 1823723 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 16.6527. Min Range: -16.6527
Max Act: 15.2777. Min Act: -0.1700
Data Index: 8385792 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 16.6527. Min Range: -16.6527
Max Act: 15.2152. Min Act: -0.1700
Data Index: 8026676 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 16.6527. Min Range: -16.6527
Max Act: 15.1527. Min Act: -0.1700
Data Index: 406049 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #19