Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2347 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0251. Min Range: -5.0251
Max Act: 5.0251. Min Act: -0.1700
Data Index: 280262 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0251. Min Range: -5.0251
Max Act: 4.9314. Min Act: -0.1700
Data Index: 902631 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0251. Min Range: -5.0251
Max Act: 4.9001. Min Act: -0.1700
Data Index: 4105072 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0251. Min Range: -5.0251
Max Act: 4.8689. Min Act: -0.1700
Data Index: 5504559 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0251. Min Range: -5.0251
Max Act: 4.8376. Min Act: -0.1700
Data Index: 3329427 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0251. Min Range: -5.0251
Max Act: 4.8376. Min Act: -0.1700
Data Index: 359549 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0251. Min Range: -5.0251
Max Act: 4.8376. Min Act: -0.1700
Data Index: 2872372 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0251. Min Range: -5.0251
Max Act: 4.7439. Min Act: -0.1700
Data Index: 7848287 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0251. Min Range: -5.0251
Max Act: 4.7439. Min Act: -0.1700
Data Index: 6759810 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0251. Min Range: -5.0251
Max Act: 4.7439. Min Act: -0.1700
Data Index: 3368988 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0251. Min Range: -5.0251
Max Act: 4.7439. Min Act: -0.1700
Data Index: 373071 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0251. Min Range: -5.0251
Max Act: 4.7439. Min Act: -0.1700
Data Index: 3220257 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0251. Min Range: -5.0251
Max Act: 4.7126. Min Act: -0.1700
Data Index: 1113542 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0251. Min Range: -5.0251
Max Act: 4.7126. Min Act: -0.1700
Data Index: 6487149 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0251. Min Range: -5.0251
Max Act: 4.7126. Min Act: -0.1700
Data Index: 2138995 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0251. Min Range: -5.0251
Max Act: 4.7126. Min Act: -0.1700
Data Index: 3297363 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0251. Min Range: -5.0251
Max Act: 4.7126. Min Act: -0.1700
Data Index: 6591244 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0251. Min Range: -5.0251
Max Act: 4.6814. Min Act: -0.1700
Data Index: 8720134 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0251. Min Range: -5.0251
Max Act: 4.6814. Min Act: -0.1700
Data Index: 4206810 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0251. Min Range: -5.0251
Max Act: 4.6501. Min Act: -0.1700
Data Index: 3699717 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #19