Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6090 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7357. Min Range: -3.7357
Max Act: 3.7357. Min Act: -0.1700
Data Index: 4593412 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7357. Min Range: -3.7357
Max Act: 3.7044. Min Act: -0.1700
Data Index: 5494557 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7357. Min Range: -3.7357
Max Act: 3.6419. Min Act: -0.1700
Data Index: 7730645 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7357. Min Range: -3.7357
Max Act: 3.6106. Min Act: -0.1700
Data Index: 7350417 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7357. Min Range: -3.7357
Max Act: 3.6106. Min Act: -0.1700
Data Index: 7695771 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7357. Min Range: -3.7357
Max Act: 3.6106. Min Act: -0.1700
Data Index: 2639244 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7357. Min Range: -3.7357
Max Act: 3.6106. Min Act: -0.1700
Data Index: 1251148 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7357. Min Range: -3.7357
Max Act: 3.6106. Min Act: -0.1700
Data Index: 8111241 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7357. Min Range: -3.7357
Max Act: 3.5792. Min Act: -0.1700
Data Index: 7336393 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7357. Min Range: -3.7357
Max Act: 3.5479. Min Act: -0.1700
Data Index: 2866872 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7357. Min Range: -3.7357
Max Act: 3.5792. Min Act: -0.1700
Data Index: 3308172 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7357. Min Range: -3.7357
Max Act: 3.5479. Min Act: -0.1700
Data Index: 2037363 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7357. Min Range: -3.7357
Max Act: 3.5792. Min Act: -0.1700
Data Index: 6747299 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7357. Min Range: -3.7357
Max Act: 3.5479. Min Act: -0.1700
Data Index: 5658490 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7357. Min Range: -3.7357
Max Act: 3.5479. Min Act: -0.1700
Data Index: 4687049 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7357. Min Range: -3.7357
Max Act: 3.5479. Min Act: -0.1700
Data Index: 522814 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7357. Min Range: -3.7357
Max Act: 3.5479. Min Act: -0.1700
Data Index: 3533617 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7357. Min Range: -3.7357
Max Act: 3.5479. Min Act: -0.1700
Data Index: 1378892 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7357. Min Range: -3.7357
Max Act: 3.4853. Min Act: -0.1700
Data Index: 363377 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7357. Min Range: -3.7357
Max Act: 3.5166. Min Act: -0.1700
Data Index: 7300460 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #19