Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1602 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1217. Min Range: -7.1217
Max Act: 7.1217. Min Act: -0.1700
Data Index: 5296023 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1217. Min Range: -7.1217
Max Act: 7.1217. Min Act: -0.1700
Data Index: 8290847 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1217. Min Range: -7.1217
Max Act: 7.0592. Min Act: -0.1700
Data Index: 4737812 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1217. Min Range: -7.1217
Max Act: 7.0280. Min Act: -0.1700
Data Index: 481256 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1217. Min Range: -7.1217
Max Act: 6.9342. Min Act: -0.1700
Data Index: 6395880 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1217. Min Range: -7.1217
Max Act: 6.8717. Min Act: -0.1700
Data Index: 3674295 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1217. Min Range: -7.1217
Max Act: 6.8717. Min Act: -0.1700
Data Index: 650759 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1217. Min Range: -7.1217
Max Act: 6.8405. Min Act: -0.1700
Data Index: 2524703 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1217. Min Range: -7.1217
Max Act: 6.8405. Min Act: -0.1700
Data Index: 6831785 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1217. Min Range: -7.1217
Max Act: 6.8092. Min Act: -0.1700
Data Index: 1620629 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1217. Min Range: -7.1217
Max Act: 6.7467. Min Act: -0.1700
Data Index: 1861097 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1217. Min Range: -7.1217
Max Act: 6.7467. Min Act: -0.1700
Data Index: 5133957 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1217. Min Range: -7.1217
Max Act: 6.7155. Min Act: -0.1700
Data Index: 6170022 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1217. Min Range: -7.1217
Max Act: 6.7155. Min Act: -0.1700
Data Index: 3549427 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1217. Min Range: -7.1217
Max Act: 6.7155. Min Act: -0.1700
Data Index: 211046 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1217. Min Range: -7.1217
Max Act: 6.6842. Min Act: -0.1700
Data Index: 5270180 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1217. Min Range: -7.1217
Max Act: 6.7155. Min Act: -0.1700
Data Index: 6675209 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1217. Min Range: -7.1217
Max Act: 6.7155. Min Act: -0.1700
Data Index: 2379744 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1217. Min Range: -7.1217
Max Act: 6.7467. Min Act: -0.1700
Data Index: 340273 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1217. Min Range: -7.1217
Max Act: 6.6842. Min Act: -0.1700
Data Index: 6694170 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #19